© 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. 1161
    Prev
    Next
    INDEX
    Explanations

    questions and uncertainties

    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
     ISNI
    -0.71
    afficheront
    -0.69
     NSCoder
    -0.66
    niająca
    -0.65
    сылкі
    -0.60
    protoimpl
    -0.59
    XmlType
    -0.59
    ImageContext
    -0.59
    ArrowToggle
    -0.58
    aronne
    -0.57
    POSITIVE LOGITS
     there
    0.62
     it
    0.59
     is
    0.59
     touches
    0.56
     hits
    0.55
     touch
    0.53
     ligt
    0.47
    theres
    0.47
     IS
    0.45
     receives
    0.44
    Activations Density 0.000%

    No Known Activations