Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4226
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
     ModelRenderer
    -0.54
    rewsbury
    -0.51
     teach
    -0.51
     Reap
    -0.49
    Rule
    -0.49
     endif
    -0.49
     JMenuItem
    -0.47
    ge
    -0.47
    cyklopedia
    -0.47
    iální
    -0.47
    POSITIVE LOGITS
    +#+#
    0.68
    GeneratedCode
    0.61
     EconPapers
    0.60
    extAlignment
    0.57
     craft
    0.56
    craft
    0.55
     HasFactory
    0.55
    CloseOperation
    0.54
     nonatomic
    0.53
     Craft
    0.52
    Activations Density 0.001%

    No Known Activations