© 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. 13554
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    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
    ter
    -0.90
     ter
    -0.67
     Ter
    -0.60
    TER
    -0.53
    uter
    -0.52
    Ter
    -0.47
    cher
    -0.47
    ium
    -0.46
    eter
    -0.40
     he
    -0.40
    POSITIVE LOGITS
    DockStyle
    1.04
    IndentedString
    1.02
    ьаж
    1.01
     CreateTagHelper
    0.93
    ConstraintMaker
    0.90
     Chwiliwch
    0.85
    دانشنامهٔ
    0.85
    SequentialGroup
    0.84
    LookAnd
    0.84
    WireFormatLite
    0.84
    Activations Density 0.025%

    No Known Activations