© 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. 1-CLT-HP
    7. 9201
    Prev
    Next
    INDEX
    Explanations

    ra

    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
     ra
    -0.72
     Ra
    -0.71
    Ra
    -0.70
    ra
    -0.60
    rava
    -0.56
     Rach
    -0.55
    ("")]
    -0.53
    RA
    -0.52
     Loose
    -0.48
     Raff
    -0.48
    POSITIVE LOGITS
    PRNewswire
    0.57
    !*\
    0.55
    offsetof
    0.54
    MigrationBuilder
    0.54
    webElement
    0.54
    MessageOf
    0.54
    ]='\
    0.54
    yntaxException
    0.53
    ItemLayout
    0.53
    setof
    0.53
    Activations Density 0.012%

    No Known Activations