© 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. 5-CLT-HP
    7. 1970
    Prev
    Next
    INDEX
    Explanations

    surveys and dissemination

    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
    SpringRunner
    -0.81
    OGND
    -0.81
    ynchronously
    -0.79
    Parcelize
    -0.78
    Portail
    -0.75
    GraphicsUnit
    -0.75
     kaynağından
    -0.74
    日閲覧
    -0.73
    IContainer
    -0.71
     GenerationType
    -0.70
    POSITIVE LOGITS
     index
    0.45
     resources
    0.37
    index
    0.37
     hand
    0.36
     collaboration
    0.35
     needs
    0.35
     am
    0.34
     pleg
    0.34
     about
    0.34
     featuring
    0.34
    Activations Density 0.002%

    No Known Activations