© 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. 0-CLT-HP
    7. 92606
    Prev
    Next
    INDEX
    Explanations

    tweaking

    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
     lists
    -0.77
    lists
    -0.69
    Lists
    -0.54
    atory
    -0.53
    HEC
    -0.53
     list
    -0.52
     debates
    -0.51
     listas
    -0.51
     expert
    -0.50
    list
    -0.50
    POSITIVE LOGITS
    InjectAttribute
    0.93
    contentLoaded
    0.84
     дописавши
    0.82
    styleType
    0.79
     chré
    0.74
    SharedDtor
    0.70
     beginnetje
    0.69
    StoryboardSegue
    0.69
    SourceChecksum
    0.68
    ParallelGroup
    0.68
    Activations Density 0.125%

    No Known Activations