© 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. 915
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    tvguidetime
    -0.86
     unknownFields
    -0.57
    farwyddwr
    -0.53
     referrerpolicy
    -0.51
    ἰ
    -0.47
     BoxFit
    -0.47
    findpost
    -0.46
    AsUp
    -0.46
    новниш
    -0.45
     patho
    -0.45
    POSITIVE LOGITS
     AssemblyVersion
    0.60
    دانشنامهٔ
    0.56
     harden
    0.56
    évaluateur
    0.54
     виправивши
    0.54
     or
    0.53
     NSM
    0.52
    GEBURTSDATUM
    0.48
    ịp
    0.48
    .‏
    0.48
    Activations Density 0.001%

    No Known Activations