© 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. 42718
    Prev
    Next
    INDEX
    Explanations

    scraping/cutting

    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
     ProtoMessage
    -0.94
     scratch
    -0.86
    OGND
    -0.81
    AnimationsModule
    -0.80
    enderror
    -0.79
    onActivityResult
    -0.79
    EndProject
    -0.78
     Crack
    -0.77
     getItemCount
    -0.76
    ]--;
    -0.76
    POSITIVE LOGITS
    s
    0.77
    sk
    0.75
    le
    0.71
    sam
    0.61
    she
    0.59
    ly
    0.57
    er
    0.56
    ler
    0.56
    system
    0.56
    sd
    0.56
    Activations Density 0.271%

    No Known Activations