© 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. 4-CLT-HP
    7. 3394
    Prev
    Next
    INDEX
    Explanations

    in

    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
     AppCompatTheme
    -0.50
    cinogen
    -0.50
    LoadScene
    -0.49
    izr
    -0.48
    EndInit
    -0.47
    HttpStatus
    -0.46
    SerializeField
    -0.46
     AssemblyProduct
    -0.46
     imageNamed
    -0.45
     alphabetically
    -0.45
    POSITIVE LOGITS
    minster
    0.58
    OCH
    0.57
    OCCURRED
    0.54
    err
    0.53
    stered
    0.52
     realidad
    0.51
    事实上
    0.51
     fact
    0.51
    cadeira
    0.51
     reality
    0.50
    Activations Density 0.003%

    No Known Activations