© 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. 5592
    Prev
    Next
    INDEX
    Explanations

    $

    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
    IsContent
    -0.51
     houver
    -0.47
     necesite
    -0.47
     uska
    -0.46
     quieran
    -0.45
     hiciera
    -0.44
    <bos>
    -0.43
    '
    -0.43
    AutoField
    -0.43
     quieras
    -0.43
    POSITIVE LOGITS
    WindowConstants
    0.74
    Šaltiniai
    0.68
    UnsafeEnabled
    0.67
    ########.
    0.63
     Audiodateien
    0.63
     Woodland
    0.60
     nether
    0.59
    KURZBESCHREIBUNG
    0.59
    ultu
    0.59
     */
    0.58
    Activations Density 0.229%

    No Known Activations