© 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. 38853
    Prev
    Next
    INDEX
    Explanations

    tised

    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
    post
    -0.85
    ecap
    -0.83
    findpost
    -0.69
     utafitiHapana
    -0.62
     autorytatywna
    -0.62
    
    -0.60
     ostavi
    -0.60
    SharedCtor
    -0.57
    awaiter
    -0.56
    LookAnd
    -0.56
    POSITIVE LOGITS
    ccia
    0.58
     defined
    0.57
     pleaſure
    0.56
    unicip
    0.54
     immunotherapy
    0.54
    ingga
    0.53
     Paredes
    0.53
     Chowdhury
    0.52
    lecular
    0.52
     JERSEY
    0.51
    Activations Density 1.965%

    No Known Activations