© 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. 0-CLT-HP
    7. 94011
    Prev
    Next
    INDEX
    Explanations

    onese

    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
    onese
    -1.13
    語
    -0.81
    rir
    -0.78
    语
    -0.69
    WriteLiteral
    -0.64
    Assurance
    -0.52
     partire
    -0.52
     infantiles
    -0.51
     语
    -0.51
     Assurance
    -0.50
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.58
    labelledby
    0.57
    AutoScaleMode
    0.56
     Meksiku
    0.56
     knocking
    0.54
    
    0.53
    XtraGrid
    0.53
    actionMode
    0.52
     '\\;'
    0.51
    ellschaft
    0.49
    Activations Density 0.646%

    No Known Activations