© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 12247
    Prev
    Next
    INDEX
    Explanations

    themes related to survival and luck in dangerous situations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISupport
    -0.49
    memoized
    -0.48
    providedIn
    -0.46
    unsch
    -0.46
    strado
    -0.46
    NullCheck
    -0.46
    ızlık
    -0.45
     rueda
    -0.45
    ঙ
    -0.45
    featureID
    -0.43
    POSITIVE LOGITS
     saved
    0.84
    saved
    0.74
     survived
    0.73
     rescued
    0.73
     Saved
    0.73
     dodged
    0.73
     evade
    0.70
    Saved
    0.70
     saving
    0.69
     saves
    0.69
    Activations Density 0.069%

    No Known Activations