© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97125
    Prev
    Next
    INDEX
    Explanations

    armp

    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
    chid
    -0.78
    ague
    -0.63
    ffe
    -0.62
    lasting
    -0.61
    cution
    -0.56
    Rourke
    -0.55
    setupUi
    -0.53
    ALARM
    -0.52
    sburg
    -0.50
    LookAnd
    -0.50
    POSITIVE LOGITS
    enumi
    0.60
     arşivlendi
    0.59
    enumii
    0.56
    DockStyle
    0.52
     دیکھیے
    0.50
    \{\\
    0.49
    styleType
    0.49
    ilik
    0.47
     جات
    0.47
    Gambas
    0.47
    Activations Density 0.832%

    No Known Activations