© 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. 0-CLT-HP
    7. 95241
    Prev
    Next
    INDEX
    Explanations

    code

    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
    -0.57
     gea
    -0.47
    chum
    -0.44
    lorette
    -0.44
    anément
    -0.43
    charCodeAt
    -0.43
     hari
    -0.42
     code
    -0.41
    zarchiwizowane
    -0.41
    ς
    -0.40
    POSITIVE LOGITS
     تانيه
    0.92
     BoxDecoration
    0.68
     femininos
    0.68
    })*/
    0.66
     gioielli
    0.65
    IVEREF
    0.65
     utafitiHapana
    0.65
     contenuti
    0.63
     automatiques
    0.63
     nahilalakip
    0.63
    Activations Density 0.128%

    No Known Activations