© 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. 4-CLT-HP
    7. 892
    Prev
    Next
    INDEX
    Explanations

    suppress

    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
    IndentedString
    -0.66
    VersionUID
    -0.58
    Havolalar
    -0.56
    rungsseite
    -0.56
    >`;
    -0.52
    CreateMap
    -0.50
    preserving
    -0.50
     GenerationType
    -0.49
     >=",
    -0.49
     Macaulay
    -0.49
    POSITIVE LOGITS
    ors
    0.63
    ant
    0.60
    alf
    0.56
    ored
    0.55
    ants
    0.54
    orst
    0.53
    ores
    0.51
     BoxDecoration
    0.51
    sess
    0.50
    věd
    0.50
    Activations Density 0.003%

    No Known Activations