© 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. 5438
    Prev
    Next
    INDEX
    Explanations

    writing

    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
     Minif
    -0.58
     tartalomajánló
    -0.58
     essays
    -0.53
    Портал
    -0.52
    KommentareTeilen
    -0.52
     essay
    -0.51
     oper
    -0.50
     Anſ
    -0.50
     Perm
    -0.50
     hook
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.85
    TypedDataSet
    0.68
    tonsoft
    0.56
     ProtoMessage
    0.56
    帖最后由
    0.55
    WebElementEntity
    0.54
     Paglinawan
    0.54
     Infórmanos
    0.54
    stdc
    0.54
    PerformLayout
    0.54
    Activations Density 0.005%

    No Known Activations