© 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. 1-CLT-HP
    7. 278
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    RegistryLite
    -0.73
     hemispheres
    -0.70
    Diwedd
    -0.69
    contentLoaded
    -0.66
    mergeFrom
    -0.64
    AISSEE
    -0.62
    ArgsConstructor
    -0.61
     Drapeau
    -0.60
     flakes
    -0.60
    adaptiveStyles
    -0.58
    POSITIVE LOGITS
     following
    0.57
    ikon
    0.47
     receiving
    0.45
    SafeAreaView
    0.45
    following
    0.44
     posting
    0.44
     setting
    0.43
     FOLLOWING
    0.42
    OfBirth
    0.42
    []):
    0.42
    Activations Density 0.805%

    No Known Activations