© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96355
    Prev
    Next
    INDEX
    Explanations

    Articles and studies

    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
    enderror
    -0.70
     quæ
    -0.65
     Connectez
    -0.59
     purpoſe
    -0.59
    )['
    -0.56
     postData
    -0.56
     Pesca
    -0.56
    stdc
    -0.56
    }`).
    -0.55
     Diſ
    -0.55
    POSITIVE LOGITS
    ,
    0.57
     (
    0.52
    rungsseite
    0.52
    migrationBuilder
    0.51
     فريبيس
    0.51
    DebuggerStep
    0.45
     архивлан
    0.45
     Signalez
    0.44
    省市镇
    0.44
    [++
    0.43
    Activations Density 0.007%

    No Known Activations