© 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. 94622
    Prev
    Next
    INDEX
    Explanations

    zzleHttp

    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
    numerusform
    -0.68
    <eos>
    -0.55
    ู
    -0.50
     Carrington
    -0.47
    esez
    -0.46
     beyond
    -0.46
    eren
    -0.45
    原始内容存档于
    -0.44
    شي
    -0.44
     Er
    -0.43
    POSITIVE LOGITS
     uſed
    0.70
     Efq
    0.68
     betweenstory
    0.65
     Majefty
    0.65
     RISERV
    0.63
     fince
    0.61
    WebVitals
    0.60
    LLocation
    0.60
     ARXIV
    0.59
    NUMX
    0.58
    Activations Density 0.574%

    No Known Activations