© 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. 12636
    Prev
    Next
    INDEX
    Explanations

    statements that involve conditional or tentative language

    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
    Negative Logits
    DockStyle
    -0.64
    SharedDtor
    -0.52
     void
    -0.47
     Empieza
    -0.46
    void
    -0.46
     propOrder
    -0.45
    rebbero
    -0.42
    XmlIgnore
    -0.42
    FDRE
    -0.42
    mcc
    -0.42
    POSITIVE LOGITS
    HasAnnotation
    0.71
    AndroidJUnit
    0.69
     condensation
    0.62
     milder
    0.61
    errHandler
    0.60
     moderate
    0.60
    さすがに
    0.59
     Somewhat
    0.59
    uttavia
    0.58
     bulunabilir
    0.58
    Activations Density 0.154%

    No Known Activations