© 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. 12991
    Prev
    Next
    INDEX
    Explanations

    practice

    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
     Normdatei
    -0.54
    rmdir
    -0.53
    kloped
    -0.52
    ":
    -0.51
    MethodManager
    -0.51
     Präsidenten
    -0.49
    `;
    -0.48
    ScopeManager
    -0.47
    zeera
    -0.46
    ".
    -0.45
    POSITIVE LOGITS
    Tikang
    0.67
    tyfik
    0.65
     colonized
    0.60
     متعلقه
    0.59
     pelota
    0.59
     talkin
    0.57
     ***!
    0.57
    encodeWith
    0.56
    libft
    0.55
     beginnetje
    0.55
    Activations Density 0.003%

    No Known Activations