© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2521
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership and power dynamics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1129
    +0.09
    0.3%
    2011
    +0.08
    0.2%
    1334
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.09
    0.05
    1034
    +0.08
    0.05
    645
    +0.08
    0.04
    Negative Logits
    umacher
    -0.63
     fameux
    -0.62
     exemplaire
    -0.61
     démarrage
    -0.61
     avancée
    -0.60
     Shipments
    -0.59
     Traces
    -0.58
     Utilisation
    -0.58
     identifiant
    -0.55
     sauvegarde
    -0.55
    POSITIVE LOGITS
     vogli
    0.75
     sappi
    0.73
    fordable
    0.72
     fasc
    0.71
     volete
    0.69
     abbiano
    0.68
     LIRE
    0.66
     vini
    0.66
     fuir
    0.65
     dè
    0.65
    Activations Density 0.266%

    No Known Activations