© 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. 76712
    Prev
    Next
    INDEX
    Explanations

    various snippets

    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
     Doo
    -0.44
     missions
    -0.43
    VersionUID
    -0.42
     InputDecoration
    -0.41
    llary
    -0.40
     Mission
    -0.39
     classic
    -0.39
    trieb
    -0.39
    lı
    -0.39
     defStyle
    -0.39
    POSITIVE LOGITS
     الحره
    0.82
     فريبيس
    0.71
    webElementXpaths
    0.70
     defaultstate
    0.69
     AttributeSet
    0.67
    ViewImports
    0.67
     question
    0.66
    tonode
    0.66
    question
    0.66
     '\\;'
    0.63
    Activations Density 0.000%

    No Known Activations