© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5550
    Prev
    Next
    INDEX
    Explanations

    6

    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
    دانشنامهٔ
    -0.96
     dAtA
    -0.77
    bootstrapcdn
    -0.72
    KommentareTeilen
    -0.71
    TagMode
    -0.71
    BeginInit
    -0.70
    ⓧ
    -0.70
    GeneratedValue
    -0.70
     Référence
    -0.70
    CloseOperation
    -0.70
    POSITIVE LOGITS
    ombie
    0.47
    worthy
    0.43
     FileNotFound
    0.40
    isFull
    0.39
    RenderAtEndOf
    0.39
    Décès
    0.37
    ็จ
    0.37
     zorro
    0.37
    4
    0.36
    Pwd
    0.36
    Activations Density 0.022%

    No Known Activations