© 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. 1-CLT-HP
    7. 11423
    Prev
    Next
    INDEX
    Explanations

    interaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.48
    i
    -0.43
    .
    -0.42
    s
    -0.41
     and
    -0.39
    ABAD
    -0.39
     affaires
    -0.37
     سازی
    -0.36
     prů
    -0.36
    mtu
    -0.35
    POSITIVE LOGITS
     ModelExpression
    0.86
     Theſe
    0.84
     Italijanski
    0.84
     Efq
    0.84
    AccessorTable
    0.83
    $.
    0.82
    '}>
    0.78
    '],
    0.78
     ]
    0.78
    новниш
    0.77
    Activations Density 0.008%

    No Known Activations