© 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. 1-CLT-HP
    7. 9195
    Prev
    Next
    INDEX
    Explanations

    is

    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
     này
    -0.59
     alcance
    -0.59
    which
    -0.59
     préc
    -0.55
    containing
    -0.55
     coû
    -0.55
     is
    -0.55
     happens
    -0.53
     suivants
    -0.53
     timmar
    -0.52
    POSITIVE LOGITS
     able
    1.13
     considered
    1.05
     not
    0.96
     seen
    0.95
     capable
    0.93
     unable
    0.92
     a
    0.91
     regarded
    0.87
     an
    0.87
     supposed
    0.85
    Activations Density 0.115%

    No Known Activations