© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1542
    Prev
    Next
    INDEX
    Explanations

    hyphenated syllables and parts of chemical or technical words

    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
     للمعارف
    -0.78
    m
    -0.77
    ly
    -0.70
    gunas
    -0.70
    s
    -0.69
     bigli
    -0.68
    ખ
    -0.68
     Agustín
    -0.66
    に
    -0.64
    ByteString
    -0.63
    POSITIVE LOGITS
    o
    1.20
    auso
    1.09
     Lando
    1.02
    eo
    0.98
    llo
    0.98
     Leno
    0.94
    ugo
    0.94
    eno
    0.93
    ITO
    0.93
     Malo
    0.93
    Activations Density 1.740%

    No Known Activations