© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 534
    Prev
    Next
    INDEX
    Explanations

    Execution

    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
    tvguidetime
    -0.60
    
    -0.57
    ReusableCell
    -0.57
     Between
    -0.52
     between
    -0.52
     EconPapers
    -0.50
    ’
    -0.50
    Between
    -0.50
     tussen
    -0.50
    between
    -0.49
    POSITIVE LOGITS
     CommonModule
    0.68
     дописавши
    0.60
    })));
    0.57
    Ἁ
    0.57
    batore
    0.57
    fige
    0.56
    }],
    0.56
     alike
    0.56
    haltens
    0.54
    Said
    0.53
    Activations Density 0.023%

    No Known Activations