© 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. 72956
    Prev
    Next
    INDEX
    Explanations

    code/technical contexts

    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
     myel
    -0.60
     незавершена
    -0.56
    elemField
    -0.55
    estimm
    -0.54
    adaptiveStyles
    -0.52
     militaires
    -0.51
     الرياضيه
    -0.49
    ScopeManager
    -0.49
     pinulongan
    -0.49
    ])->
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.69
    Seznam
    0.58
    INCREF
    0.54
     DP
    0.54
    Xna
    0.54
    COV
    0.54
     cov
    0.53
     AttributeSet
    0.52
    idl
    0.51
    DP
    0.50
    Activations Density 0.000%

    No Known Activations