© 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. 0-CLT-HP
    7. 93718
    Prev
    Next
    INDEX
    Explanations

    statements of fact/effect

    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
    fact
    -0.59
     fact
    -0.56
     hecho
    -0.48
    læ
    -0.48
    europa
    -0.48
     adapted
    -0.47
    되어
    -0.47
     szen
    -0.46
     bero
    -0.45
     GE
    -0.45
    POSITIVE LOGITS
     caufe
    0.68
     purpoſe
    0.67
    OGND
    0.66
    vernight
    0.65
     pleaſure
    0.65
    RenderAtEndOf
    0.64
     reaſon
    0.63
     myſelf
    0.63
    KommentareTeilen
    0.61
     Majefty
    0.60
    Activations Density 0.087%

    No Known Activations