© 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. 20-CLT-HP
    7. 73024
    Prev
    Next
    INDEX
    Explanations

    say [the dash]

    np_max-act-logits · 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
    ="@+
    -0.68
     <>",
    -0.61
    IContainer
    -0.61
     <<<<<<<<<<<<<<
    -0.60
     Chwiliwch
    -0.59
     logan
    -0.57
     Maude
    -0.56
    RuleContext
    -0.55
     resourceCulture
    -0.55
    mybatisplus
    -0.53
    POSITIVE LOGITS
    â
    0.61
    -
    0.58
    �
    0.51
    вЂ
    0.48
    ?
    0.46
    –
    0.45
    jsxFileName
    0.44
    ¿½
    0.41
    ‭
    0.40
    鈥
    0.40
    Activations Density 0.021%

    No Known Activations