© 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. 17530
    Prev
    Next
    INDEX
    Explanations

    conditional statements and the expression of uncertainty or questioning in reasoning

    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
    -0.54
    <eos>
    -0.46
     SIMBAD
    -0.46
    nofollow
    -0.44
    ↵↵
    -0.42
    keyColumn
    -0.40
     note
    -0.39
     generali
    -0.39
    .”
    -0.38
    mpotent
    -0.38
    POSITIVE LOGITS
     Efq
    1.12
     myſelf
    1.03
     Majefty
    1.01
     itſelf
    0.98
     pleaſure
    0.93
     ſever
    0.92
     Houſe
    0.91
     raiſ
    0.90
     faſt
    0.89
     Theſe
    0.89
    Activations Density 0.599%

    No Known Activations