© 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. 3-RES-MATRYOSHKA-DC
    7. 3134
    Prev
    Next
    INDEX
    Explanations

    strings enclosed in square brackets and starting with `[@B`

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.90
     Shakspeare
    -0.83
     DBNull
    -0.81
     Theſe
    -0.78
     Anſ
    -0.75
     getB
    -0.75
     Majefty
    -0.73
     Bute
    -0.71
     Efq
    -0.71
     itſelf
    -0.71
    POSITIVE LOGITS
    rimid
    0.47
    <bos>
    0.46
    uyang
    0.44
     the
    0.42
    ouz
    0.41
    uming
    0.40
    teilt
    0.40
    rahmen
    0.40
    übers
    0.40
     hiszen
    0.40
    Activations Density 0.107%

    No Known Activations