© 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. 15871
    Prev
    Next
    INDEX
    Explanations

    machine learning/technical texts

    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
    defineProperty
    -0.57
     незавершена
    -0.53
     createState
    -0.49
     Sahib
    -0.49
     Circuits
    -0.48
    NOPQRST
    -0.45
     defaultstate
    -0.45
    setVerticalGroup
    -0.45
     BorderRadius
    -0.44
     CascadeType
    -0.44
    POSITIVE LOGITS
     tartalomajánló
    0.62
    ,:);
    0.60
    SharedDtor
    0.54
    TALL
    0.53
     ogóle
    0.53
    )++;
    0.53
     Partager
    0.52
    〗
    0.50
     mergeFrom
    0.50
    \"");
    0.49
    Activations Density 0.034%

    No Known Activations