© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90559
    Prev
    Next
    INDEX
    Explanations

    forgiveness

    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
    ✨:
    -0.90
    TestingModule
    -0.87
    AxisAlignment
    -0.83
    AddTagHelper
    -0.75
    CompilerServices
    -0.74
     AssemblyCulture
    -0.72
    Tikang
    -0.70
     createdBy
    -0.67
     Inscrivez
    -0.65
     AttributeSet
    -0.65
    POSITIVE LOGITS
    ıllı
    0.46
    el
    0.45
    bewerken
    0.43
     препратки
    0.42
    U
    0.42
    adpleegd
    0.40
     싶
    0.39
    event
    0.39
    uns
    0.37
    ele
    0.37
    Activations Density 1.238%

    No Known Activations