© 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. 6312
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    mota
    -0.44
    uyler
    -0.41
     Inaug
    -0.40
    ngOnInit
    -0.40
    ethene
    -0.40
    onReady
    -0.40
    opo
    -0.38
     Dora
    -0.37
    Inaug
    -0.37
    UARY
    -0.37
    POSITIVE LOGITS
     BoxFit
    0.77
     EClass
    0.71
    :✨
    0.71
     createSlice
    0.69
    Diwedd
    0.68
    InputBorder
    0.67
     resourceCulture
    0.67
    extAlignment
    0.67
    AndEndTag
    0.63
     Normdatei
    0.63
    Activations Density 0.001%

    No Known Activations