© 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. 1522
    Prev
    Next
    INDEX
    Explanations

    Date/extension

    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
     extension
    -1.35
    extension
    -1.28
    Extension
    -1.23
     Extension
    -1.19
    extended
    -1.13
     extended
    -1.10
    ext
    -1.06
     extensions
    -0.99
     named
    -0.98
     ext
    -0.97
    POSITIVE LOGITS
    ness
    0.81
    ConstraintMaker
    0.68
     DbType
    0.64
    mesg
    0.61
    KURZBESCHREIBUNG
    0.60
    regal
    0.59
    EndInit
    0.56
    rophes
    0.56
    SerializedSize
    0.56
    المكان
    0.56
    Activations Density 0.140%

    No Known Activations