© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96218
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency

    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
     menudo
    -0.57
     multe
    -0.54
    ,:);
    -0.53
    LookAnd
    -0.52
    =?";
    -0.51
    rawtypes
    -0.49
    abilir
    -0.47
    ノロ
    -0.47
    ]$}
    -0.47
    ことなく
    -0.47
    POSITIVE LOGITS
    +#+
    0.73
     accompanies
    0.67
     associated
    0.65
    TintMode
    0.65
    mybatisplus
    0.59
     allied
    0.58
    ANTLR
    0.58
    pyx
    0.58
     jadx
    0.57
    ंदीखरीदारी
    0.55
    Activations Density 0.005%

    No Known Activations