© 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. 20-CLT-HP
    7. 78171
    Prev
    Next
    INDEX
    Explanations

    code and programming

    np_max-act-logits · 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
    InjectAttribute
    -0.67
    脚注の使い方
    -0.56
    onsor
    -0.56
     protoimpl
    -0.55
     يتيمه
    -0.53
    )))
    -0.50
    istoitu
    -0.50
    unknownFields
    -0.50
     Saltar
    -0.49
    曖昧さ回避
    -0.49
    POSITIVE LOGITS
    enumi
    0.58
    gogo
    0.52
     Besch
    0.52
    蚪
    0.50
    Cyfeiriadau
    0.49
    indari
    0.49
     ProtoMessage
    0.49
    BeginContext
    0.48
     initComponents
    0.48
    AutoSize
    0.47
    Activations Density 0.000%

    No Known Activations