© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44042
    Prev
    Next
    INDEX
    Explanations

    cheaper

    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
     concept
    -0.79
     cheaper
    -0.76
     shorter
    -0.73
    concept
    -0.60
    #+#
    -0.60
    hole
    -0.59
    UIColor
    -0.59
    ///</
    -0.58
    ofition
    -0.56
    ocusing
    -0.56
    POSITIVE LOGITS
     kasarigan
    1.05
    LookAnd
    0.61
     AssemblyTitle
    0.57
    ModelSerializer
    0.54
    Билгалдахарш
    0.53
    vgili
    0.53
     للاسماء
    0.51
     Enix
    0.50
     ExecuteAsync
    0.49
     <<<<<<<<<<<<<<
    0.47
    Activations Density 0.069%

    No Known Activations