© 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. 95625
    Prev
    Next
    INDEX
    Explanations

    proposals and trials

    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
     proposal
    -1.75
     Proposal
    -1.34
    proposal
    -1.34
     proposals
    -1.24
    Proposal
    -1.22
     Proposals
    -1.05
     suggestion
    -0.99
    Proposals
    -0.94
     trials
    -0.93
    proposals
    -0.92
    POSITIVE LOGITS
     ویکی‌پدیا
    0.69
     himſelf
    0.68
     themſelves
    0.66
     myſelf
    0.63
     صوتيه
    0.62
     Bioaccumulative
    0.62
     poffe
    0.59
    ſelf
    0.59
    berdayakan
    0.59
     ویکی‌پدی
    0.56
    Activations Density 0.070%

    No Known Activations