© 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. 91950
    Prev
    Next
    INDEX
    Explanations

    surfaces and interfaces

    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
    faces
    -1.42
     surfaces
    -1.12
    FACES
    -1.08
    faced
    -1.06
     faces
    -1.05
     Majefty
    -1.02
    Faces
    -1.00
     pleaſure
    -0.99
    facing
    -0.98
     Surfaces
    -0.95
    POSITIVE LOGITS
    chism
    0.54
    e
    0.51
     rest
    0.48
    h
    0.47
     pratiques
    0.46
    delse
    0.46
     fondamental
    0.45
     rodillas
    0.45
     
    0.44
    a
    0.43
    Activations Density 1.711%

    No Known Activations