© 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. 1224
    Prev
    Next
    INDEX
    Explanations

    play

    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>
    -0.66
     play
    -0.64
     played
    -0.60
     plays
    -0.54
    OGND
    -0.53
    träd
    -0.53
    play
    -0.52
     joue
    -0.52
    الإنجليزية
    -0.50
     мѣ
    -0.50
    POSITIVE LOGITS
    setupUi
    0.68
    glEnd
    0.56
     algorithm
    0.56
    Crazy
    0.51
     Vk
    0.51
     PHPUnit
    0.50
     fair
    0.50
     MatDialog
    0.50
     "");
    0.49
     computation
    0.49
    Activations Density 0.053%

    No Known Activations