© 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. 20-CLT-HP
    7. 77738
    Prev
    Next
    INDEX
    Explanations

    code/technical language

    np_max-act-logits · 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
    tagHelperRunner
    -0.75
     autorytatywna
    -0.69
     kaarangay
    -0.66
    TargetException
    -0.64
    PhysRev
    -0.64
     defaultstate
    -0.64
     onCancelled
    -0.63
    حياتها
    -0.60
     незавершена
    -0.60
     convertView
    -0.59
    POSITIVE LOGITS
    psack
    0.45
     EClass
    0.42
    Всем
    0.42
     morreu
    0.41
    ImageContext
    0.40
    🥕
    0.40
     biologique
    0.39
    ContentAlignment
    0.39
    ILayout
    0.38
    unction
    0.37
    Activations Density 0.000%

    No Known Activations