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. 11066
    Prev
    Next
    INDEX
    Explanations

    Windows software

    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
    <bos>
    -0.82
    MigrationBuilder
    -0.64
    __*/
    -0.61
    atguigu
    -0.58
    AutoField
    -0.57
     deſt
    -0.52
     raiſ
    -0.52
     mind
    -0.52
     InputDecoration
    -0.51
     ſhe
    -0.49
    POSITIVE LOGITS
    ToBounds
    0.62
     विश्वसनीयता
    0.61
    })).
    0.59
    geen
    0.54
     Lordships
    0.54
     Routing
    0.53
     PCL
    0.53
    CodeAttribute
    0.53
    }.
    
    0.52
     Receiver
    0.51
    Activations Density 0.089%

    No Known Activations