© 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. 92169
    Prev
    Next
    INDEX
    Explanations

    go

    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
    adaptiveStyles
    -0.75
     defaultstate
    -0.66
    clusive
    -0.50
    Bioaccumulative
    -0.50
    EndContext
    -0.47
    uolo
    -0.47
    ymce
    -0.46
    intree
    -0.46
     dialami
    -0.45
     nahilalakip
    -0.45
    POSITIVE LOGITS
     wrong
    0.97
    fjspx
    0.75
    wrong
    0.69
     incorrect
    0.68
    Wrong
    0.67
     Wrong
    0.66
     worse
    0.64
     aw
    0.63
     incorrectly
    0.63
     faulty
    0.63
    Activations Density 0.003%

    No Known Activations