© 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. 5-CLT-HP
    7. 6155
    Prev
    Next
    INDEX
    Explanations

    code

    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
    Negative Logits
     vectorstock
    -0.78
     tph
    -0.66
     doubtnut
    -0.64
     Maude
    -0.63
    principalColumn
    -0.62
     dreamstime
    -0.60
     Vulcan
    -0.60
    atase
    -0.60
     Tid
    -0.59
     Apa
    -0.58
    POSITIVE LOGITS
    enumi
    0.48
    enstein
    0.45
     familiare
    0.45
    HomeAsUpEnabled
    0.44
    KommentareTeilen
    0.43
    ApiModelProperty
    0.43
    eman
    0.43
    bel
    0.42
    enej
    0.42
    enging
    0.42
    Activations Density 0.038%

    No Known Activations