© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1890
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    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
     is
    -0.90
     has
    -0.90
     will
    -0.76
     may
    -0.73
     can
    -0.72
    }';
    -0.67
     might
    -0.67
     takes
    -0.66
     could
    -0.65
    `);
    -0.65
    POSITIVE LOGITS
     AssemblyTitle
    0.64
     the
    0.59
    DllImport
    0.59
    Personensuche
    0.55
     poffible
    0.54
    ESSO
    0.52
    awakeFromNib
    0.51
     <<<<<<<<<<<<<<
    0.50
    MigrationBuilder
    0.50
     teammates
    0.49
    Activations Density 0.007%

    No Known Activations