© 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. 13139
    Prev
    Next
    INDEX
    Explanations

    sending emails

    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
     bezeichneter
    -0.61
    hört
    -0.53
     poussière
    -0.52
     certes
    -0.48
     vôtre
    -0.47
    danke
    -0.47
     fourrure
    -0.47
    zwischen
    -0.47
     hoor
    -0.46
     ✭✭
    -0.46
    POSITIVE LOGITS
    XtraGrid
    0.65
    tagHelperRunner
    0.58
    principalColumn
    0.57
    ::_('
    0.55
    IsContent
    0.53
    IntentFilter
    0.52
    WillAppear
    0.50
    invokeLater
    0.50
    ImageContext
    0.49
     ISNI
    0.48
    Activations Density 0.066%

    No Known Activations