© 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. 16129
    Prev
    Next
    INDEX
    Explanations

    folding

    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
    <bos>
    -1.02
     bū
    -0.54
    AddField
    -0.48
    ↵↵
    -0.46
    binant
    -0.45
    unggulan
    -0.44
     bílá
    -0.44
     overras
    -0.44
    Cair
    -0.43
     popoli
    -0.43
    POSITIVE LOGITS
     kaynağından
    0.79
     BoxFit
    0.63
    Personendaten
    0.60
    BagConstraints
    0.60
    enumii
    0.59
     Roskov
    0.59
     CascadeType
    0.58
     utafitiHapana
    0.56
    λώ
    0.55
     Parenthood
    0.55
    Activations Density 0.010%

    No Known Activations