© 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. 91181
    Prev
    Next
    INDEX
    Explanations

    dust

    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
     himo
    -0.63
     linkovi
    -0.63
    liferay
    -0.60
     newOwner
    -0.59
    menter
    -0.55
    ciutto
    -0.54
    Configurer
    -0.53
    InvalidProtocol
    -0.50
    mapStateToProps
    -0.50
     Stag
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    0.70
    ReusableCell
    0.63
    s
    0.51
    dymyr
    0.50
     للمعارف
    0.49
    sticks
    0.44
    tinyos
    0.43
     kuhusu
    0.43
    pty
    0.42
    seteq
    0.42
    Activations Density 0.002%

    No Known Activations