© 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. 1-CLT-HP
    7. 12195
    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
    ärna
    -0.50
    names
    -0.48
     way
    -0.48
    一一
    -0.47
    posito
    -0.47
    AutoresizingMask
    -0.47
     Way
    -0.46
    wakili
    -0.46
     MatDialog
    -0.45
    fony
    -0.45
    POSITIVE LOGITS
    mtrl
    0.65
    ArgsConstructor
    0.64
     otomatig
    0.64
     Fewer
    0.60
    ########.
    0.59
     للاسماء
    0.59
     الرياضيه
    0.58
    +:+
    0.57
    はじめに
    0.56
    SharedDtor
    0.55
    Activations Density 0.053%

    No Known Activations