© 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. 20-CLT-HP
    7. 75666
    Prev
    Next
    INDEX
    Explanations

    Code, song titles, formal writing

    np_max-act-logits · 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
     .
    -0.71
    Personensuche
    -0.61
     “.
    -0.60
     your
    -0.58
     my
    -0.57
     viewDidLoad
    -0.57
     `.
    -0.56
     ".
    -0.55
     Your
    -0.53
     .”
    -0.52
    POSITIVE LOGITS
     peindre
    0.63
     Cram
    0.57
    sé
    0.56
    fok
    0.56
    Boh
    0.56
    )\}$
    0.55
    assemblée
    0.54
     prévenir
    0.54
    ClassNotFound
    0.53
    GetWindow
    0.53
    Activations Density 0.001%

    No Known Activations