© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3830
    Prev
    Next
    INDEX
    Explanations

    embody

    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
     ModelExpression
    -0.95
     Normdatei
    -0.86
    UnusedPrivate
    -0.86
    évaluateur
    -0.84
     AssemblyTitle
    -0.82
    __(/*!
    -0.82
    +#+#
    -0.82
    featureID
    -0.81
     AssemblyCulture
    -0.79
     estekak
    -0.78
    POSITIVE LOGITS
     cross
    0.42
    Response
    0.40
     to
    0.39
     towards
    0.39
     va
    0.38
     development
    0.36
     multiple
    0.36
    новништво
    0.36
     a
    0.35
     toward
    0.35
    Activations Density 0.000%

    No Known Activations