© 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. 0-CLT-HP
    7. 94081
    Prev
    Next
    INDEX
    Explanations

    memor

    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
    ities
    -0.92
    art
    -0.78
    HasAnnotation
    -0.75
    principalColumn
    -0.68
     art
    -0.66
    ITIES
    -0.63
    MigrationBuilder
    -0.63
    artz
    -0.62
    atories
    -0.60
    born
    -0.59
    POSITIVE LOGITS
     Houſe
    0.75
     RSSSF
    0.67
     Efq
    0.65
     Conſ
    0.59
    VersionUID
    0.58
     tere
    0.58
     Shakspeare
    0.58
     Cæsar
    0.56
     Nauka
    0.56
     Inſ
    0.55
    Activations Density 1.666%

    No Known Activations