© 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. 91889
    Prev
    Next
    INDEX
    Explanations

    online discussions

    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
    UniformLocation
    -0.50
     vân
    -0.42
    aarrggbb
    -0.42
    ########.
    -0.41
    ча
    -0.41
    ,
    -0.41
    //}
    -0.40
    Clik
    -0.40
     MacGregor
    -0.40
    kla
    -0.40
    POSITIVE LOGITS
     themſelves
    0.73
     itſelf
    0.72
    ^(@)
    0.70
     Efq
    0.70
     myſelf
    0.69
     himſelf
    0.69
     Prior
    0.68
    prior
    0.68
     Chrif
    0.68
     Jefus
    0.67
    Activations Density 0.001%

    No Known Activations