© 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. 5-CLT-HP
    7. 92231
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    onAttach
    -0.71
     JADX
    -0.71
    
    -0.70
    GeneratedValue
    -0.66
     compréhen
    -0.66
    Przypisy
    -0.63
    hairs
    -0.60
    Примечания
    -0.59
     useStyles
    -0.58
    ://"
    -0.58
    POSITIVE LOGITS
    клопе
    0.69
    Iden
    0.41
     appelez
    0.40
     massive
    0.40
    poon
    0.39
     plan
    0.39
    IComponent
    0.38
    QMetaType
    0.38
     œuvre
    0.37
    Extensive
    0.37
    Activations Density 0.001%

    No Known Activations