© 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. 5965
    Prev
    Next
    INDEX
    Explanations

    the

    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
     cref
    -0.52
     "'");
    -0.44
     *);
    -0.41
    ')";
    -0.40
    XmlAccessorType
    -0.38
    Viitteet
    -0.37
    ","");
    -0.37
     chiave
    -0.36
     akt
    -0.36
     key
    -0.35
    POSITIVE LOGITS
     ExecuteAsync
    0.71
    
    0.64
    Portail
    0.62
     препратки
    0.62
    OpenHelper
    0.61
    eload
    0.60
     iprot
    0.60
    izzera
    0.60
    obiety
    0.60
    ScopeManager
    0.60
    Activations Density 0.003%

    No Known Activations