© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96266
    Prev
    Next
    INDEX
    Explanations

    wars and history

    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
     besz
    -0.46
    selt
    -0.41
    آیا
    -0.40
     of
    -0.40
     plötzlich
    -0.38
     surla
    -0.38
    ifx
    -0.37
    тко
    -0.37
    ówczas
    -0.37
     yalnızca
    -0.37
    POSITIVE LOGITS
     AspNetCore
    0.84
    HasAnnotation
    0.84
    ArgsConstructor
    0.81
     resourceCulture
    0.80
    +#+#
    0.78
     مشين
    0.77
     doInBackground
    0.76
     itſelf
    0.75
     المعيارى
    0.75
    OGND
    0.74
    Activations Density 0.005%

    No Known Activations