© 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. 5-CLT-HP
    7. 91716
    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
    Warmly
    -0.47
     zaj
    -0.47
    ="@+
    -0.46
    Jeografia
    -0.46
     blister
    -0.46
     ujednoznacz
    -0.45
    tip
    -0.45
    ore
    -0.44
    uch
    -0.44
    éez
    -0.43
    POSITIVE LOGITS
    httphttps
    0.66
    Дереккөздер
    0.61
    Litteratur
    0.60
     Efq
    0.57
     Réponses
    0.57
    BagConstraints
    0.55
     religione
    0.54
    kezett
    0.54
    Referencer
    0.53
    adecimal
    0.52
    Activations Density 0.084%

    No Known Activations