© 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. 0-CLT-HP
    7. 95436
    Prev
    Next
    INDEX
    Explanations

    writing

    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
    <bos>
    -0.71
    transQ
    -0.66
     fourrure
    -0.59
    BagLayout
    -0.56
     feroit
    -0.56
     ritratto
    -0.56
     répondit
    -0.54
    WriteTagHelper
    -0.54
     rémun
    -0.53
    NewGuid
    -0.53
    POSITIVE LOGITS
     fact
    0.78
     way
    0.72
     case
    0.61
    vay
    0.59
    iro
    0.58
     manner
    0.57
     effect
    0.56
     question
    0.56
     rhestr
    0.55
     form
    0.54
    Activations Density 0.053%

    No Known Activations