© 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. 307
    Prev
    Next
    INDEX
    Explanations

    authorities

    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
     of
    -0.43
     Bo
    -0.41
    ɒ
    -0.39
    ius
    -0.38
     keskus
    -0.38
    brainly
    -0.38
    HasBeenSet
    -0.38
    기
    -0.37
    stości
    -0.36
     Tight
    -0.36
    POSITIVE LOGITS
    AndEndTag
    0.88
     myſelf
    0.84
     Monfieur
    0.75
    ſelf
    0.73
     fhew
    0.71
     <<<<<<<<<<<<<<
    0.70
     createState
    0.69
    IUrlHelper
    0.69
     itſelf
    0.68
    ſelves
    0.68
    Activations Density 0.072%

    No Known Activations