© 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. 4927
    Prev
    Next
    INDEX
    Explanations

    realm

    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
    AMES
    -0.56
    on
    -0.51
    AME
    -0.50
    BURGH
    -0.49
    oses
    -0.48
    Browsable
    -0.47
    allon
    -0.46
    roch
    -0.46
    ucas
    -0.46
     Tra
    -0.46
    POSITIVE LOGITS
    󠁢
    0.67
    édrale
    0.65
     snippetHide
    0.65
     Efq
    0.65
     Мексичка
    0.65
    enderror
    0.60
    eador
    0.57
    脚注の使い方
    0.57
    — 
    0.57
     greateſt
    0.56
    Activations Density 0.000%

    No Known Activations