© 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. 5-CLT-HP
    7. 3460
    Prev
    Next
    INDEX
    Explanations

    academic texts

    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
    Jereo
    -0.66
     ligiloj
    -0.66
     initComponents
    -0.63
     فريبيس
    -0.62
     חיצוניים
    -0.59
    pfung
    -0.57
     Mehl
    -0.56
     дописавши
    -0.56
    adpleegd
    -0.55
    蚪
    -0.55
    POSITIVE LOGITS
     DAP
    0.51
    DAP
    0.49
    TagMode
    0.48
     Barrow
    0.48
     continúas
    0.48
     Hift
    0.47
     pleaf
    0.46
    CrossRef
    0.46
     dau
    0.46
    hibian
    0.45
    Activations Density 0.001%

    No Known Activations