© 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. 15899
    Prev
    Next
    INDEX
    Explanations

    Ț

    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
     éco
    -0.42
    tanleria
    -0.41
    uaikan
    -0.38
    brtc
    -0.38
    ter
    -0.38
     suivant
    -0.38
    exp
    -0.36
    덜
    -0.36
     sorprend
    -0.35
    ,
    -0.34
    POSITIVE LOGITS
     дописавши
    0.98
    ftagPool
    0.90
    AndEndTag
    0.89
     pinulongan
    0.81
     transfieras
    0.79
    sizeCache
    0.77
    +#+#
    0.77
     transférez
    0.73
    الدراسه
    0.72
    InjectAttribute
    0.69
    Activations Density 0.104%

    No Known Activations