© 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. 91938
    Prev
    Next
    INDEX
    Explanations

    sections

    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
     Section
    -1.09
    Section
    -0.84
     spill
    -0.80
     spilled
    -0.80
     spills
    -0.69
    spill
    -0.65
     <<<<<<<<<<<<<<
    -0.63
     spilling
    -0.58
     spilt
    -0.58
     backs
    -0.57
    POSITIVE LOGITS
    AutoScale
    0.65
    otide
    0.59
    ighed
    0.54
    SupportActionBar
    0.54
    routeProvider
    0.53
    kopp
    0.53
    IComponent
    0.52
    resave
    0.52
     AppComponent
    0.52
     Specimens
    0.50
    Activations Density 0.233%

    No Known Activations