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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3135
    Prev
    Next
    INDEX
    Explanations

    Could not determine the neuron's behavior.transfer

    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
     trial
    -0.56
     Smarty
    -0.50
     député
    -0.49
     Trial
    -0.47
    ="{{$
    -0.46
     createSprite
    -0.46
     annak
    -0.45
    skyl
    -0.45
    Versch
    -0.45
    nix
    -0.45
    POSITIVE LOGITS
    Hentet
    0.76
    tagHelperRunner
    0.70
    CodedInputStream
    0.58
    hark
    0.57
     resultCode
    0.57
    elemField
    0.54
    DBNull
    0.53
    httphttps
    0.53
     Meksiku
    0.53
    InputBorder
    0.51
    Activations Density 0.002%

    No Known Activations