© 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. 14617
    Prev
    Next
    INDEX
    Explanations

    phrases related to presidential pardons

    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
    1105
    +0.09
    0.3%
    222
    +0.09
    0.2%
    919
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1287
    +0.09
    0.03
    1105
    +0.09
    0.04
    919
    +0.08
    0.02
    Negative Logits
     increa
    -0.99
     purcha
    -0.99
     guarante
    -0.98
     affor
    -0.95
     strick
    -0.91
     encomp
    -0.90
     prouve
    -0.90
     wherea
    -0.90
     scrat
    -0.90
     prétend
    -0.89
    POSITIVE LOGITS
     forgiveness
    0.79
     forgiven
    0.71
     pardon
    0.69
     forgive
    0.66
     forgiving
    0.63
     amnesty
    0.62
     pardoned
    0.61
     mercy
    0.61
     granted
    0.58
     pard
    0.56
    Activations Density 0.415%

    No Known Activations