© 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. 4537
    Prev
    Next
    INDEX
    Explanations

    ISD

    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
    +#+#
    -0.69
     springfox
    -0.64
    XmlAccessType
    -0.57
    cyklopedia
    -0.54
    principalTable
    -0.54
     resourceCulture
    -0.54
    WebControls
    -0.53
    IntoConstraints
    -0.53
     nahilalakip
    -0.53
    multirow
    -0.52
    POSITIVE LOGITS
     Efq
    0.63
    )))));
    0.59
    DoubleQuotes
    0.59
    ſelf
    0.58
    omyelitis
    0.57
     Spisak
    0.56
    ();)
    0.56
    ()")
    0.56
    ',['
    0.56
    queous
    0.55
    Activations Density 2.096%

    No Known Activations