© 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. 5691
    Prev
    Next
    INDEX
    Explanations

    much/lot

    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
    detectChanges
    -0.60
     препратки
    -0.54
    WillAppear
    -0.51
     Spisak
    -0.46
    cobra
    -0.46
     hơi
    -0.44
    fatal
    -0.44
    WriteBarrier
    -0.43
    cshtml
    -0.43
     هيا
    -0.43
    POSITIVE LOGITS
     else
    1.03
    extAlignment
    0.71
    else
    0.71
     الاطلاع
    0.67
     reaſon
    0.57
     ELSE
    0.56
     consultato
    0.55
     pleaſure
    0.53
    ("")]
    0.53
     Else
    0.52
    Activations Density 0.003%

    No Known Activations