© 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. 0-CLT-HP
    4. 44156
    Prev
    Next
    INDEX
    Explanations

    ice/storm

    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
     getItemId
    -0.58
     coincidence
    -0.51
     beſt
    -0.51
    tly
    -0.49
    ocellular
    -0.49
     Monfieur
    -0.48
     taint
    -0.48
     reconcile
    -0.48
     Jefus
    -0.47
    pable
    -0.47
    POSITIVE LOGITS
    TagMode
    0.60
    contentLoaded
    0.58
    ⓘ
    0.57
     Circ
    0.57
     Ramp
    0.57
     Cent
    0.56
     Centre
    0.54
    uxxxx
    0.54
     Car
    0.54
     Head
    0.54
    Activations Density 0.260%

    No Known Activations