© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93838
    Prev
    Next
    INDEX
    Explanations

    group

    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
     group
    -1.30
    group
    -1.01
     Group
    -1.01
    Group
    -0.96
     GROUP
    -0.83
     grupo
    -0.81
     Gruppe
    -0.79
     gruppo
    -0.77
    GROUP
    -0.76
     gruppe
    -0.74
    POSITIVE LOGITS
     وتسجيلات
    0.80
    Tikang
    0.72
     tartalomajánló
    0.68
     సౌకర్య
    0.66
     chi̍t
    0.66
     conçus
    0.65
     BoxFit
    0.64
     marquées
    0.63
    djangoproject
    0.60
    adaptiveStyles
    0.57
    Activations Density 0.041%

    No Known Activations