© 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. 97807
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    BeginContext
    -0.72
    SharedDtor
    -0.69
     nakalista
    -0.68
    windowFixed
    -0.68
     disambiguazione
    -0.66
    Хьажоргаш
    -0.65
    InitVars
    -0.65
    politan
    -0.58
    ########.
    -0.57
    ZZO
    -0.57
    POSITIVE LOGITS
    G
    0.68
    I
    0.65
    M
    0.60
    T
    0.60
    W
    0.58
     المعيارى
    0.57
    B
    0.57
    N
    0.57
    F
    0.56
    K
    0.56
    Activations Density 0.002%

    No Known Activations