© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1125
    Prev
    Next
    INDEX
    Explanations

    magic

    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
    parsedMessage
    -0.80
     relève
    -0.74
    RegistryLite
    -0.73
    migrationBuilder
    -0.72
     malheure
    -0.71
     iprot
    -0.70
    enumi
    -0.69
    tanleria
    -0.69
    enumii
    -0.66
     ostavi
    -0.66
    POSITIVE LOGITS
     sound
    0.53
     pen
    0.53
     ring
    0.52
     word
    0.47
     sl
    0.44
     Sloan
    0.44
     effect
    0.43
     spell
    0.43
     mat
    0.42
     com
    0.41
    Activations Density 0.013%

    No Known Activations