© 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. 4427
    Prev
    Next
    INDEX
    Explanations

    Change has occurred

    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
     overexpression
    -0.53
     ExecuteAsync
    -0.47
    ReusableCell
    -0.45
    不等
    -0.42
    chaun
    -0.41
     recently
    -0.41
    setViewportView
    -0.40
    SourceChecksum
    -0.40
    DoubleQuotes
    -0.39
    vernote
    -0.39
    POSITIVE LOGITS
    lloworld
    0.61
     então
    0.61
    WriteBarrier
    0.61
    NameInMap
    0.60
    LookAnd
    0.60
    Vidite
    0.60
    depuis
    0.59
     بلکه
    0.59
    since
    0.58
     asimismo
    0.58
    Activations Density 0.007%

    No Known Activations