© 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. 5-CLT-HP
    7. 4330
    Prev
    Next
    INDEX
    Explanations

    sports

    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
    ulipas
    -0.53
     Garrison
    -0.43
    jface
    -0.42
    ulae
    -0.41
    TableHead
    -0.41
    uch
    -0.41
     CURIAM
    -0.40
     Gop
    -0.40
    PAP
    -0.39
     Palin
    -0.39
    POSITIVE LOGITS
    NameInMap
    0.93
    matchCondition
    0.84
    Personensuche
    0.78
    rungsseite
    0.74
    SBATCH
    0.69
    الحياه
    0.68
    WillAppear
    0.66
     estimés
    0.64
    GraphicsUnit
    0.63
     pinulongan
    0.63
    Activations Density 0.007%

    No Known Activations