© 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. 77409
    Prev
    Next
    INDEX
    Explanations

    Software and code

    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
    ChildScrollView
    -0.62
    ImageContext
    -0.61
    Identyfik
    -0.60
    PullParser
    -0.59
     estekak
    -0.58
    SupportActionBar
    -0.56
    MigrationBuilder
    -0.56
    putan
    -0.55
    SharedCtor
    -0.54
    ChildIndex
    -0.54
    POSITIVE LOGITS
    ISTICS
    0.52
     setuptools
    0.51
     considérons
    0.43
    getWriter
    0.42
    dfunding
    0.41
    ox
    0.40
    iecie
    0.39
    grafos
    0.38
    onimo
    0.38
     (!_
    0.38
    Activations Density 0.000%

    No Known Activations