© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13408
    Prev
    Next
    INDEX
    Explanations

    Law, contamination, research

    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
    astă
    -0.51
    updateOne
    -0.49
     cliquant
    -0.47
     OSError
    -0.46
    em
    -0.45
    TabStop
    -0.44
    GenerationType
    -0.43
    igshid
    -0.42
     endwhile
    -0.42
    BASEPATH
    -0.42
    POSITIVE LOGITS
     الرياضيه
    0.70
    ArgsConstructor
    0.68
     Cuthbert
    0.60
     JpaRepository
    0.59
    garder
    0.58
     bogotá
    0.58
    ukone
    0.56
     Escrow
    0.56
     Pender
    0.56
    urator
    0.55
    Activations Density 0.028%

    No Known Activations