© 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. 5117
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     كومونز
    -0.90
    DoubleQuotes
    -0.85
    Cyfarwyddwr
    -0.76
    ChildScrollView
    -0.74
     فريبيس
    -0.73
    AutoresizingMask
    -0.72
     snippetHide
    -0.70
    URLException
    -0.69
    styleType
    -0.69
     InputDecoration
    -0.68
    POSITIVE LOGITS
     dimenti
    0.50
    jścia
    0.49
    FURTHER
    0.47
     internetowa
    0.46
     kesan
    0.45
    DidChange
    0.45
    talt
    0.44
    unità
    0.44
     menerima
    0.44
     giao
    0.43
    Activations Density 0.001%

    No Known Activations