© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8961
    Prev
    Next
    INDEX
    Explanations

    atory, tone

    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
     GenerationType
    -0.66
    sel
    -0.51
    semp
    -0.50
    bitField
    -0.50
    led
    -0.44
    AddTagHelper
    -0.44
    стоин
    -0.44
    eled
    -0.43
    tika
    -0.42
     kū
    -0.42
    POSITIVE LOGITS
    ⓧ
    0.76
     estekak
    0.69
    itoneal
    0.64
     Pergamon
    0.64
    TagHelpers
    0.61
     Anſ
    0.60
     myſelf
    0.60
     jsPsych
    0.60
     IgA
    0.60
     ganglia
    0.59
    Activations Density 0.081%

    No Known Activations