© 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. 4-CLT-HP
    7. 211
    Prev
    Next
    INDEX
    Explanations

    the

    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
    最快更新
    -0.64
    Hentet
    -0.63
    httphttps
    -0.61
     disambiguazione
    -0.60
     Púb
    -0.52
    MigrationBuilder
    -0.51
     cherchés
    -0.50
    GEBURTSDATUM
    -0.49
     ✭✭
    -0.49
     NSCoder
    -0.48
    POSITIVE LOGITS
    ]--;
    0.67
    mité
    0.52
    irmar
    0.51
     stomachs
    0.50
    ]++;
    0.50
     shaded
    0.49
    )')
    0.49
     distance
    0.48
     clear
    0.48
    drücken
    0.48
    Activations Density 0.002%

    No Known Activations