© 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. 5-CLT-HP
    7. 93686
    Prev
    Next
    INDEX
    Explanations

    changes and time

    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
    aarrggbb
    -0.94
    OrNil
    -0.73
     חיצוניים
    -0.73
    protoimpl
    -0.68
    ividual
    -0.67
    ')))
    -0.66
    Rüyada
    -0.66
    SharedCtor
    -0.66
    ]<<"
    -0.65
     "..\..\
    -0.65
    POSITIVE LOGITS
     since
    0.63
     for
    0.57
     to
    0.55
    ,
    0.50
     after
    0.47
     now
    0.47
     under
    0.46
    since
    0.44
     but
    0.43
    .
    0.42
    Activations Density 0.004%

    No Known Activations