© 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. 6004
    Prev
    Next
    INDEX
    Explanations

    size/measurements

    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
    twimg
    -0.90
    LookAnd
    -0.88
     дописавши
    -0.81
    WebVitals
    -0.79
    httphttps
    -0.78
    CloseOperation
    -0.76
    igshid
    -0.75
    
    -0.75
    awtextra
    -0.72
    __(/*!
    -0.72
    POSITIVE LOGITS
     troubled
    0.47
     troublesome
    0.45
    toHave
    0.44
     distur
    0.41
    einander
    0.41
    一般
    0.41
    шње
    0.40
     burdened
    0.40
     trouble
    0.39
     palmas
    0.39
    Activations Density 0.014%

    No Known Activations