© 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. 5280
    Prev
    Next
    INDEX
    Explanations

    solids

    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
     المعيارى
    -0.86
     StatefulWidget
    -0.80
    SequentialGroup
    -0.75
    AndEndTag
    -0.70
    InjectAttribute
    -0.69
     ModelExpression
    -0.69
    InstrumentedTest
    -0.68
     يتيمه
    -0.65
    الحياه
    -0.63
    PropertyChanging
    -0.63
    POSITIVE LOGITS
     Klan
    0.54
    tuk
    0.50
    ophila
    0.49
     triangulation
    0.49
    SPO
    0.48
     Armed
    0.44
    aku
    0.43
    endian
    0.42
     triang
    0.42
     revi
    0.41
    Activations Density 0.024%

    No Known Activations