© 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. 1-CLT-HP
    7. 11730
    Prev
    Next
    INDEX
    Explanations

    roads and surfaces

    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
    gms
    -0.57
    SharedDtor
    -0.57
     متعلقه
    -0.55
    CppCodeGen
    -0.50
     ब्रेकडाउन
    -0.49
     ibid
    -0.48
    ">//
    -0.48
     hinaus
    -0.48
    AsUp
    -0.47
    WebMethod
    -0.47
    POSITIVE LOGITS
    ⓧ
    0.59
     paradise
    0.57
    Sprintf
    0.56
    principalTable
    0.54
     trajets
    0.54
    ANSION
    0.51
    dillos
    0.51
    wunsch
    0.50
    SBATCH
    0.50
    cheiben
    0.50
    Activations Density 0.009%

    No Known Activations