© 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. 5-CLT-HP
    7. 1014
    Prev
    Next
    INDEX
    Explanations

    online interactions

    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
    Œuvres
    -0.52
     onOptions
    -0.50
    WithIOException
    -0.46
    /***/
    -0.45
     ArrayAdapter
    -0.44
    struts
    -0.44
    InstanceState
    -0.42
    IBAction
    -0.42
    flashdata
    -0.41
    --*/
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.73
    Hentet
    0.71
     iprot
    0.70
    RegressionTest
    0.69
    ambién
    0.68
     total
    0.65
    twimg
    0.65
     totales
    0.63
     totale
    0.62
    Total
    0.61
    Activations Density 0.004%

    No Known Activations