© 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. 71796
    Prev
    Next
    INDEX
    Explanations

    technical/informational context

    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
    ...@
    -0.59
    TargetException
    -0.57
    uyez
    -0.52
    Mediabestanden
    -0.52
    XtraReports
    -0.52
     it
    -0.50
    urably
    -0.50
    Finishing
    -0.49
    onAttach
    -0.47
    UnknownFields
    -0.46
    POSITIVE LOGITS
     might
    0.65
    ніципа
    0.62
     is
    0.60
     could
    0.59
     Италијани
    0.59
    кипедия
    0.56
    ьаж
    0.56
    bewerken
    0.55
    Abitanti
    0.54
     may
    0.53
    Activations Density 0.002%

    No Known Activations