© 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. 94975
    Prev
    Next
    INDEX
    Explanations

    migrations

    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
     giapp
    -0.56
    curité
    -0.54
    herzog
    -0.54
    Попис
    -0.54
     comiendo
    -0.54
     HttpNotFound
    -0.54
    enumii
    -0.51
     klart
    -0.51
     tué
    -0.51
     voorzien
    -0.51
    POSITIVE LOGITS
     onCreateView
    0.57
    abstractmethod
    0.52
     formal
    0.52
    şiv
    0.50
     referral
    0.50
    ditional
    0.49
     costly
    0.49
    erialized
    0.49
     professional
    0.48
    Abp
    0.48
    Activations Density 0.001%

    No Known Activations