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. 11063
    Prev
    Next
    INDEX
    Explanations

    Rear

    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
    Rear
    -0.61
     Rear
    -0.59
    rear
    -0.52
     برانيه
    -0.42
    Clayton
    -0.42
     հղումներ
    -0.42
     CURIAM
    -0.41
    picasso
    -0.41
    الحياه
    -0.41
    stdc
    -0.40
    POSITIVE LOGITS
    )";
    
    0.65
    extAlignment
    0.62
    */;
    0.59
    Chham
    0.58
    InSection
    0.57
    $_['
    0.56
    ranging
    0.56
    geth
    0.56
    FieldBuilder
    0.56
     Beam
    0.55
    Activations Density 0.002%

    No Known Activations