© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38954
    Prev
    Next
    INDEX
    Explanations

    s

    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
     the
    -0.88
     their
    -0.68
     respectivement
    -0.67
     a
    -0.61
    the
    -0.57
     an
    -0.56
     these
    -0.54
     this
    -0.52
     gouttes
    -0.52
     stationnement
    -0.51
    POSITIVE LOGITS
    }],
    
    0.69
    }]
    
    0.63
     kasarigan
    0.62
    BeginContext
    0.62
     pinulongan
    0.62
     NSCoder
    0.61
    ritation
    0.60
    GEBURTSDATUM
    0.60
     boroughs
    0.59
    UnitTesting
    0.59
    Activations Density 0.036%

    No Known Activations