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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 2101
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of uncertainty or doubt

    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
    featureID
    -0.72
     Roskov
    -0.68
    EndContext
    -0.65
    farin
    -0.63
    adaptiveStyles
    -0.63
    цездатний
    -0.59
    enterOuterAlt
    -0.57
    addCriterion
    -0.57
    ʖ
    -0.56
     Poincar
    -0.56
    POSITIVE LOGITS
     seldom
    0.56
     nonetheless
    0.56
    {}'.
    0.56
    $")
    0.56
    {}".
    0.56
    ("")]
    0.55
    それでも
    0.54
    ürnberg
    0.53
    "):
    0.52
    それにしても
    0.52
    Activations Density 0.518%

    No Known Activations