© 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. 20-CLT-HP
    7. 72566
    Prev
    Next
    INDEX
    Explanations

    pem

    np_max-act-logits · 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
    Meyer
    -0.52
    afficheront
    -0.50
     Meyer
    -0.49
    тру
    -0.48
    AutoScaleMode
    -0.48
     net
    -0.47
     Kahn
    -0.47
    ptus
    -0.47
    Dud
    -0.47
    net
    -0.47
    POSITIVE LOGITS
    __":
    0.69
     Roskov
    0.64
     שוליים
    0.61
    帖最后由
    0.59
    __':
    0.56
    WriteBarrier
    0.55
    exitRule
    0.54
    IconModule
    0.54
    BufferException
    0.53
    InjectAttribute
    0.53
    Activations Density 0.001%

    No Known Activations