© 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. 5-CLT-HP
    7. 5667
    Prev
    Next
    INDEX
    Explanations

    commas and slashes

    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
     already
    -0.52
    ske
    -0.48
    ting
    -0.45
    ree
    -0.43
     the
    -0.42
     Already
    -0.42
     who
    -0.42
    er
    -0.41
    hee
    -0.41
    ho
    -0.41
    POSITIVE LOGITS
     nahilalakip
    0.86
     defaultstate
    0.82
    styleType
    0.81
    findpost
    0.81
    sidemargin
    0.80
     ویکی‌پدیای
    0.79
     unknownFields
    0.76
    Autoritní
    0.74
    لينكات
    0.72
     otomatig
    0.72
    Activations Density 0.080%

    No Known Activations