© 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. 12157
    Prev
    Next
    INDEX
    Explanations

    weakened

    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
     Team
    -0.48
    ueba
    -0.47
    +");
    -0.46
     kasarigan
    -0.45
     Shoot
    -0.44
     Part
    -0.43
    AccessorTable
    -0.43
    Team
    -0.43
     serez
    -0.42
     Group
    -0.42
    POSITIVE LOGITS
    Rüyada
    0.65
     intStringLen
    0.65
     AssemblyProduct
    0.64
    ьаж
    0.63
    brainly
    0.60
     AssemblyCompany
    0.59
    EndGlobalSection
    0.59
     UIAlert
    0.56
    orah
    0.56
    Disliked
    0.56
    Activations Density 0.019%

    No Known Activations