Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12670
    Prev
    Next
    INDEX
    Explanations

    their

    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
     appellee
    -0.59
    sidemargin
    -0.58
    thargy
    -0.57
     Vikipedi
    -0.55
    EndContext
    -0.55
     asunder
    -0.54
    enfone
    -0.54
     interlocutor
    -0.53
     useAppContext
    -0.52
    tvguidetime
    -0.50
    POSITIVE LOGITS
     som
    0.61
     sos
    0.54
     Treated
    0.53
     borg
    0.53
    ≦)
    0.52
     sinn
    0.51
    burg
    0.50
    Amérique
    0.50
     Business
    0.50
    べき
    0.50
    Activations Density 0.058%

    No Known Activations