© 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. 14410
    Prev
    Next
    INDEX
    Explanations

    neurotransmitters and prediction

    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
    Diwedd
    -0.76
     onCancelled
    -0.72
     للاسماء
    -0.67
     ProtoMessage
    -0.62
    InitVars
    -0.61
    APORE
    -0.60
    ApiModelProperty
    -0.60
     propOrder
    -0.59
    enumi
    -0.59
     &___
    -0.58
    POSITIVE LOGITS
    ంది
    0.44
    POINTER
    0.43
     gradient
    0.41
     grits
    0.41
     Loire
    0.40
    werb
    0.40
     peso
    0.40
     Gr
    0.40
     bucket
    0.40
     Thesaurus
    0.40
    Activations Density 0.028%

    No Known Activations