© 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. 20-CLT-HP
    7. 76723
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and technical terms

    np_max-act-logits · 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
    ]";
    -0.62
    ^(@)
    -0.60
    apimachinery
    -0.58
     Putih
    -0.55
    .*")]
    -0.55
    }`;
    -0.54
    }';
    -0.53
    ')";
    -0.51
    Abitanti
    -0.50
     primate
    -0.50
    POSITIVE LOGITS
     tractors
    0.70
    InSection
    0.69
    EndInit
    0.68
     combine
    0.56
     tractor
    0.56
     combines
    0.54
    combine
    0.50
    ScopeManager
    0.50
     Tractor
    0.50
    Impl
    0.49
    Activations Density 0.001%

    No Known Activations