© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2351
    Prev
    Next
    INDEX
    Explanations

    actions related to fleeing or escaping

    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
    204
    +0.12
    0.4%
    1895
    +0.12
    0.3%
    197
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.12
    0.03
    946
    +0.12
    0.03
    944
    +0.09
    0.02
    Negative Logits
     poteva
    -0.51
     voleva
    -0.50
    FieldOffset
    -0.48
    Getenv
    -0.45
     conosce
    -0.44
     doveva
    -0.44
     numberWith
    -0.43
    ReusableCell
    -0.43
    DateTimeFormat
    -0.42
    ScreenWidth
    -0.42
    POSITIVE LOGITS
     flee
    0.92
     fleeing
    0.82
    fled
    0.72
     fled
    0.69
    phazard
    0.57
     insensible
    0.57
    FTFY
    0.56
     sula
    0.55
     resultList
    0.55
     Hæ
    0.54
    Activations Density 0.137%

    No Known Activations