© 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. 0-CLT-HP
    7. 94120
    Prev
    Next
    INDEX
    Explanations

    VP

    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
    horst
    -0.59
    VP
    -0.49
    ouwd
    -0.49
    lindungan
    -0.47
     VP
    -0.47
    vor
    -0.46
    fame
    -0.45
     Würde
    -0.45
    ScopeManager
    -0.44
    izade
    -0.44
    POSITIVE LOGITS
    🏼
    0.64
    ed
    0.60
    ized
    0.59
    CPtr
    0.58
     defStyle
    0.57
    ness
    0.57
    +:+
    0.57
    🏽
    0.56
    🏾
    0.55
     AssemblyCompany
    0.54
    Activations Density 0.294%

    No Known Activations