© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10548
    Prev
    Next
    INDEX
    Explanations

    named

    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
     jspb
    -0.61
    FromNib
    -0.58
    INSTALLED
    -0.58
    -------------</
    -0.56
     createSlice
    -0.56
     againſt
    -0.55
     لينك
    -0.55
    ftagPool
    -0.54
    JKLM
    -0.54
     bandai
    -0.53
    POSITIVE LOGITS
     Exacts
    0.49
    èse
    0.46
     estekak
    0.46
    rungsseite
    0.45
    sivi
    0.44
    zzi
    0.44
    holt
    0.44
     Ferner
    0.43
    >{"
    0.43
    Kjelder
    0.42
    Activations Density 0.012%

    No Known Activations