© 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. 92297
    Prev
    Next
    INDEX
    Explanations

    music

    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
    ParallelGroup
    -0.66
    elernt
    -0.60
     defaultstate
    -0.54
    ]]:
    -0.50
    脚注の使い方
    -0.48
    CppCodeGen
    -0.47
     >=",
    -0.46
    IsContent
    -0.46
     تانيه
    -0.46
    inspired
    -0.45
    POSITIVE LOGITS
    Personensuche
    0.62
    Viited
    0.55
     passés
    0.54
    ...@
    0.53
    rungsseite
    0.52
    cookieParser
    0.49
    discussions
    0.49
    .
    0.49
     About
    0.49
     kyse
    0.49
    Activations Density 0.000%

    No Known Activations