© 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. 20-CLT-HP
    7. 73410
    Prev
    Next
    INDEX
    Explanations

    or

    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
    ftagPool
    -0.88
    ReusableCell
    -0.85
    Tikang
    -0.78
     فريبيس
    -0.76
    出版年
    -0.74
     imageNamed
    -0.73
     beginnetje
    -0.70
     sumpay
    -0.70
    scriptcase
    -0.67
    IsContent
    -0.67
    POSITIVE LOGITS
    voz
    0.50
     plus
    0.46
    oq
    0.44
    Jeografia
    0.42
    plus
    0.41
    respect
    0.36
     setOpen
    0.35
    organization
    0.35
     rond
    0.34
    ides
    0.34
    Activations Density 0.001%

    No Known Activations