© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10948
    Prev
    Next
    INDEX
    Explanations

    Digestive system

    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
     HasFactory
    -0.76
     normaux
    -0.67
     positifs
    -0.67
    Przypisy
    -0.63
    клопе
    -0.62
     présidenti
    -0.62
     colorés
    -0.62
     fidé
    -0.61
     剪影
    -0.58
     curieux
    -0.58
    POSITIVE LOGITS
    }";
    0.49
    ResponseWriter
    0.44
    AutoScale
    0.44
    PathVariable
    0.44
    detectChanges
    0.44
    demia
    0.42
    }';
    0.41
    が高い
    0.39
    attack
    0.38
    PENG
    0.38
    Activations Density 0.029%

    No Known Activations