© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45647
    Prev
    Next
    INDEX
    Explanations

    vote

    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
     vote
    -0.97
    vote
    -0.78
     Vote
    -0.66
    Vote
    -0.65
     voted
    -0.65
     votes
    -0.63
     VOTE
    -0.60
    TacToe
    -0.60
    Portale
    -0.59
    XmlAccessType
    -0.57
    POSITIVE LOGITS
     Paglinawan
    0.52
     direct
    0.51
    hame
    0.49
    tesse
    0.49
    ksis
    0.48
    ائص
    0.47
    PAGER
    0.47
    lessness
    0.47
    apur
    0.46
     Paix
    0.46
    Activations Density 0.009%

    No Known Activations