© 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. 20-CLT-HP
    7. 76007
    Prev
    Next
    INDEX
    Explanations

    K

    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
     mergeFrom
    -0.62
    RegressionTest
    -0.51
    iedad
    -0.50
    oretical
    -0.49
    UnitTesting
    -0.48
    boro
    -0.48
    photobucket
    -0.47
     FormBuilder
    -0.47
    tifact
    -0.47
    Попис
    -0.46
    POSITIVE LOGITS
    లాలు
    0.64
    AutoField
    0.60
     effects
    0.56
     Effects
    0.54
     Roskov
    0.53
    Effects
    0.53
     Magal
    0.52
     Effect
    0.51
    giène
    0.50
    Spoljašnje
    0.50
    Activations Density 0.001%

    No Known Activations