© 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. 1-CLT-HP
    7. 10187
    Prev
    Next
    INDEX
    Explanations

    point

    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
    point
    -1.02
    LookAnd
    -0.98
     point
    -0.92
    POINT
    -0.90
    Point
    -0.90
    points
    -0.85
     Point
    -0.84
     POINT
    -0.81
    XmlEnum
    -0.78
    oredCriteria
    -0.75
    POSITIVE LOGITS
     of
    0.65
     hereof
    0.55
     Sociales
    0.48
    __(/*!
    0.48
    of
    0.47
     florales
    0.47
     darbo
    0.44
    e
    0.44
    MockBean
    0.44
    <bos>
    0.43
    Activations Density 1.169%

    No Known Activations