© 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. 4-CLT-HP
    7. 525
    Prev
    Next
    INDEX
    Explanations

    Sample

    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
     handker
    -0.70
    thâu
    -0.65
     Shakspeare
    -0.65
     Efq
    -0.62
     picioare
    -0.61
    UnsafeEnabled
    -0.60
    omitempty
    -0.59
     Borel
    -0.58
     Monfieur
    -0.58
    VIAF
    -0.57
    POSITIVE LOGITS
     vérit
    0.50
    BeginContext
    0.50
    jarat
    0.49
    ffler
    0.48
    Uwagi
    0.48
     comment
    0.47
    vasti
    0.47
     dan
    0.46
    исленность
    0.46
     vœux
    0.45
    Activations Density 0.010%

    No Known Activations