© 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. 92457
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
    <bos>
    -0.85
    TypedDataSet
    -0.63
    SourceChecksum
    -0.62
    ParallelGroup
    -0.58
    MigrationBuilder
    -0.56
    ValueStyle
    -0.50
    AddHtmlAttribute
    -0.50
     <<<<<<<<<<<<<<
    -0.49
     Lec
    -0.48
     Ong
    -0.47
    POSITIVE LOGITS
     homeowners
    0.65
     everything
    0.65
     you
    0.61
     Everything
    0.58
    onAttach
    0.54
     kids
    0.53
    Everything
    0.53
     EVERYTHING
    0.52
     swimmers
    0.52
    minecraftforge
    0.52
    Activations Density 0.001%

    No Known Activations