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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95085
    Prev
    Next
    INDEX
    Explanations

    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
     sentito
    -0.60
     préf
    -0.57
     felt
    -0.54
     know
    -0.54
     knew
    -0.54
     amoureux
    -0.54
     préféré
    -0.53
     knows
    -0.52
     hoeft
    -0.52
    RTLD
    -0.50
    POSITIVE LOGITS
     discussed
    0.70
     discusses
    0.65
     stated
    0.59
     typelib
    0.58
    secta
    0.57
    verwijspagina
    0.57
     outlined
    0.57
     explained
    0.55
    kloped
    0.55
    discussed
    0.54
    Activations Density 0.002%

    No Known Activations