© 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. 4-CLT-HP
    7. 1346
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     único
    -0.53
    protoimpl
    -0.51
    schaft
    -0.50
    šanai
    -0.49
    
    -0.49
    providedIn
    -0.49
     soltanto
    -0.48
    ſelf
    -0.47
     titolata
    -0.47
     herself
    -0.47
    POSITIVE LOGITS
     any
    0.71
     it
    0.71
    .*")]
    0.68
     թվական
    0.67
     reaching
    0.63
     disambiguazione
    0.63
     they
    0.63
     the
    0.60
    örd
    0.60
     we
    0.59
    Activations Density 0.002%

    No Known Activations