© 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. 45599
    Prev
    Next
    INDEX
    Explanations

    zero

    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
     zeros
    -0.66
     nonzero
    -0.60
     to
    -0.59
     zero
    -0.54
    zeros
    -0.51
     &___
    -0.50
     podjela
    -0.50
    الدراسه
    -0.49
    CompleteListener
    -0.48
    CloseOperation
    -0.48
    POSITIVE LOGITS
    uxxxx
    0.71
    kháu
    0.68
     depositphotos
    0.61
     Meksiku
    0.60
     HttpNotFound
    0.59
     ProtoMessage
    0.56
    HomeAsUp
    0.55
    enko
    0.55
     fotográfica
    0.54
    WithEmail
    0.53
    Activations Density 0.027%

    No Known Activations