Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12895
    Prev
    Next
    INDEX
    Explanations

    reach

    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
    Reaching
    -0.50
     reach
    -0.45
     atteindre
    -0.42
    enumii
    -0.42
     bereiken
    -0.41
    îné
    -0.41
     reaching
    -0.40
    }{|
    -0.40
    antaranya
    -0.40
    Reach
    -0.39
    POSITIVE LOGITS
    principalTable
    0.83
     utafitiHapana
    0.80
    PerformLayout
    0.79
     AssemblyTitle
    0.79
    WriteTagHelper
    0.79
    ⓧ
    0.78
    OGND
    0.76
    LookAnd
    0.75
    ThroughAttribute
    0.69
    StructEnd
    0.66
    Activations Density 0.010%

    No Known Activations