© 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. 5-CLT-HP
    7. 6154
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    freopen
    -0.53
    Demografie
    -0.51
    osi
    -0.50
    ordano
    -0.50
    òn
    -0.50
     jspb
    -0.49
    openha
    -0.47
     UserDao
    -0.47
    ús
    -0.46
     VIDEOTAPE
    -0.46
    POSITIVE LOGITS
    ly
    0.64
     ECA
    0.56
    脚注の使い方
    0.52
    хьтан
    0.52
    Jill
    0.52
    eafter
    0.51
    Personensuche
    0.50
    下载附件
    0.50
    adpleegd
    0.49
    ண்டும்
    0.49
    Activations Density 0.005%

    No Known Activations