© 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. 4-CLT-HP
    7. 1765
    Prev
    Next
    INDEX
    Explanations

    DEC

    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
    帖最后由
    -0.62
     <=",
    -0.57
    θεν
    -0.55
    UnknownFields
    -0.54
    曖昧さ回避
    -0.52
     Justices
    -0.52
    NOPQRST
    -0.52
     pinulongan
    -0.51
     réessayer
    -0.48
     Autorisations
    -0.48
    POSITIVE LOGITS
    قایناق‌لار
    0.58
     محفوظة
    0.57
    QMetaType
    0.57
    WindowConstants
    0.53
     utafitiHapana
    0.53
     söyl
    0.53
    Демографія
    0.52
    OMS
    0.49
     Logement
    0.49
    ayaquil
    0.48
    Activations Density 0.001%

    No Known Activations