© 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. 95082
    Prev
    Next
    INDEX
    Explanations

    technical/administrative documents

    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
    ✨:
    -0.86
     mourut
    -0.77
     eût
    -0.75
    PointerException
    -0.73
    niosek
    -0.71
     AssemblyProduct
    -0.71
     Efq
    -0.71
    Erreferentziak
    -0.71
    featureID
    -0.70
     étoit
    -0.68
    POSITIVE LOGITS
     find
    0.52
     will
    0.52
     develop
    0.49
    om
    0.45
     may
    0.45
     get
    0.44
     evolve
    0.44
     become
    0.44
     start
    0.43
     solve
    0.42
    Activations Density 0.001%

    No Known Activations