© 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. 15027
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    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
     ordinaires
    -0.60
    archiviato
    -0.55
     orizz
    -0.54
    bach
    -0.51
    pend
    -0.50
     réguli
    -0.50
     fraî
    -0.49
     polaire
    -0.48
     popolari
    -0.47
     seguras
    -0.47
    POSITIVE LOGITS
    ArgsConstructor
    0.67
    aarrggbb
    0.65
    ukone
    0.60
     Normdatei
    0.60
    titutions
    0.56
    EndContext
    0.56
    TintMode
    0.55
    dataclass
    0.54
    ]))
    0.54
    oriam
    0.53
    Activations Density 0.017%

    No Known Activations