© 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. 15315
    Prev
    Next
    INDEX
    Explanations

    region

    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
    FieldBuilder
    -0.63
     TextEditing
    -0.58
    wußt
    -0.57
    umenter
    -0.52
    uyer
    -0.51
     UITableViewCell
    -0.51
     Référence
    -0.50
     onPostExecute
    -0.50
    లాలు
    -0.50
     InputDecoration
    -0.49
    POSITIVE LOGITS
     disambiguazione
    0.61
    HasForeignKey
    0.60
    });*/
    0.50
    MessageOf
    0.50
    zimy
    0.48
     GENERATED
    0.47
    czaj
    0.47
    unanje
    0.46
    GPP
    0.46
    ttemberg
    0.45
    Activations Density 0.002%

    No Known Activations