© 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. 1-CLT-HP
    7. 14030
    Prev
    Next
    INDEX
    Explanations

    hydrothermal

    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
    entile
    -2.42
    endum
    -1.36
     pinulongan
    -0.66
    IsMutable
    -0.60
    toplankton
    -0.60
    centiles
    -0.58
    DeleteBehavior
    -0.56
     Superhost
    -0.55
    )++;
    -0.54
    urator
    -0.53
    POSITIVE LOGITS
    findpost
    0.65
    tagHelperRunner
    0.60
    testens
    0.55
     suivantes
    0.54
    LookAndFeel
    0.53
     jScrollPane
    0.50
     ويكيپيديا
    0.47
     uintptr
    0.47
    <tbody>
    0.46
    Retrouvez
    0.45
    Activations Density 0.020%

    No Known Activations