© 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. 38779
    Prev
    Next
    INDEX
    Explanations

    anywhere

    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
     anywhere
    -2.25
    anywhere
    -1.91
     Anywhere
    -1.74
     somewhere
    -1.63
    somewhere
    -1.43
    Anywhere
    -1.31
     nowhere
    -1.30
     Somewhere
    -1.20
     irgendwo
    -1.11
    Somewhere
    -1.06
    POSITIVE LOGITS
     ***!
    0.54
     Spies
    0.53
     else
    0.53
    ISupport
    0.52
    enfants
    0.51
     Gens
    0.48
    romole
    0.46
    GROUPS
    0.46
    demort
    0.45
     Pilots
    0.45
    Activations Density 0.081%

    No Known Activations