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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2449
    Prev
    Next
    INDEX
    Explanations

    glimpse

    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
     ModelExpression
    -0.66
     فريبيس
    -0.62
    Jeografia
    -0.60
     Normdatei
    -0.58
    LayoutConstraint
    -0.58
    olol
    -0.58
     protoimpl
    -0.57
    WebVitals
    -0.55
    protoimpl
    -0.54
     насељу
    -0.52
    POSITIVE LOGITS
     into
    0.63
    oredCriteria
    0.54
     FileNotFound
    0.53
    Journalist
    0.51
    estanding
    0.51
    nonatomic
    0.50
    IARC
    0.49
     of
    0.49
    الدراسه
    0.48
     tilbake
    0.47
    Activations Density 0.016%

    No Known Activations