© 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. 96112
    Prev
    Next
    INDEX
    Explanations

    Rumors/speculation/doubt

    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
    });*/
    -0.77
    uxxxx
    -0.69
     Theſe
    -0.69
    Espèce
    -0.68
    raulic
    -0.63
     chande
    -0.63
     theſe
    -0.63
    BufferException
    -0.63
     <>",
    -0.63
     ſeveral
    -0.62
    POSITIVE LOGITS
     FBref
    0.45
     Tibet
    0.44
    setAccessible
    0.43
    oría
    0.42
     questions
    0.42
    simpleType
    0.41
     growing
    0.41
    
    0.41
    рос
    0.40
     Iran
    0.40
    Activations Density 0.010%

    No Known Activations