© 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. 1-CLT-HP
    7. 8960
    Prev
    Next
    INDEX
    Explanations

    salts and symbols

    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
     ComVisible
    -0.67
     تضيفلها
    -0.66
     Meksiku
    -0.65
     متعلقه
    -0.65
     Lightboxes
    -0.65
    ThroughAttribute
    -0.64
     protoimpl
    -0.63
     salts
    -0.61
    abestanden
    -0.59
    EndProject
    -0.59
    POSITIVE LOGITS
     useHistory
    0.54
    apimachinery
    0.53
     стаття
    0.45
     metav
    0.45
     useNavigate
    0.45
    endpush
    0.44
    IBarButtonItem
    0.44
     SAC
    0.44
    oku
    0.42
     useDispatch
    0.42
    Activations Density 0.017%

    No Known Activations