© 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. 5-CLT-HP
    7. 800
    Prev
    Next
    INDEX
    Explanations

    /

    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
     CreateTagHelper
    -0.80
    BrowserModule
    -0.67
    ">//
    -0.66
    AddTagHelper
    -0.65
     Италијани
    -0.64
     saites
    -0.64
     BrowserModule
    -0.63
    addGap
    -0.63
    VolleyError
    -0.61
    GeoNames
    -0.59
    POSITIVE LOGITS
    čke
    0.53
    cases
    0.49
    Endian
    0.48
    muo
    0.47
     Staub
    0.46
    arning
    0.46
    file
    0.46
     Zahn
    0.45
    poche
    0.45
     sorgen
    0.45
    Activations Density 0.069%

    No Known Activations