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. 22-CLT-HP
    4. 74218
    Prev
    Next
    INDEX
    Explanations

    Technical and diverse topics

    np_max-act-logits · 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
    -0.79
    <?
    -0.57
    GRANTED
    -0.56
     Amadeus
    -0.53
    клопе
    -0.53
     Psychotherapy
    -0.53
    ListItemIcon
    -0.51
    Pyx
    -0.51
     Exactos
    -0.50
     Viola
    -0.49
    POSITIVE LOGITS
    WaitGroup
    0.59
    LookAnd
    0.57
    MigrationBuilder
    0.56
    EndGlobalSection
    0.56
    sprüng
    0.52
    odus
    0.50
    SequentialGroup
    0.49
    rceil
    0.47
    DeleteMapping
    0.47
     оригіналу
    0.46
    Activations Density 0.008%

    No Known Activations