© 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. 0-CLT-HP
    7. 91926
    Prev
    Next
    INDEX
    Explanations

    Technical/article context

    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
    vai
    -0.90
    urned
    -0.87
    olese
    -0.83
    hiri
    -0.60
    igration
    -0.60
     Vai
    -0.59
     doi
    -0.57
    Vai
    -0.55
     confronti
    -0.53
    cosx
    -0.47
    POSITIVE LOGITS
    RectangleBorder
    0.69
    ViewFeatures
    0.68
     незавершена
    0.64
    TestingModule
    0.62
     صوتيه
    0.62
     فريبيس
    0.61
    argout
    0.60
    Portale
    0.59
    posedge
    0.59
    NullCheck
    0.59
    Activations Density 0.952%

    No Known Activations