© 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. 12115
    Prev
    Next
    INDEX
    Explanations

    Rs

    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
     Bole
    -1.21
    Bole
    -0.94
     bole
    -0.68
    StoryboardSegue
    -0.60
     consummation
    -0.59
    /*
    -0.55
     utafitiHapana
    -0.54
    ✭✭
    -0.54
    UserContext
    -0.54
    eficent
    -0.53
    POSITIVE LOGITS
    yn
    0.55
     bornes
    0.47
    GrantedAuthority
    0.46
    kloped
    0.43
    Ответ
    0.42
     noires
    0.42
     vern
    0.42
    SaveChangesAsync
    0.41
    YN
    0.41
    irmish
    0.41
    Activations Density 0.008%

    No Known Activations