© 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. 92800
    Prev
    Next
    INDEX
    Explanations

    below

    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
    enschappelijke
    -0.55
    mannian
    -0.50
    enschappe
    -0.48
    ?')
    -0.48
     specialty
    -0.47
    pless
    -0.47
     current
    -0.47
     Topic
    -0.46
     =",
    -0.46
     Haupts
    -0.46
    POSITIVE LOGITS
    rungsseite
    0.81
    .
    0.63
    //
    0.59
    expandindo
    0.57
     >=",
    0.55
    prefixer
    0.54
     lumineuse
    0.53
     OMITBAD
    0.53
     parlant
    0.52
    ViewImports
    0.52
    Activations Density 0.001%

    No Known Activations