© 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. 72809
    Prev
    Next
    INDEX
    Explanations

    Mixed sources and languages

    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
    SourceChecksum
    -0.85
    CodedInputStream
    -0.79
    GEBURTSDATUM
    -0.65
     noDo
    -0.64
    WireFormatLite
    -0.63
     Administrativna
    -0.62
    UnitTesting
    -0.61
    _;
    -0.59
    IndentedString
    -0.59
     Roskov
    -0.59
    POSITIVE LOGITS
     mason
    0.55
    ter
    0.48
     Mason
    0.44
    mason
    0.44
    ContentLoaded
    0.43
     Ball
    0.42
     Orient
    0.42
    Mason
    0.42
     MASON
    0.42
     Archer
    0.41
    Activations Density 0.000%

    No Known Activations