© 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. 4488
    Prev
    Next
    INDEX
    Explanations

    total of

    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
     autorytatywna
    -0.83
     propOrder
    -0.79
    AsUp
    -0.68
    (__('
    -0.64
     Wiktionnaire
    -0.64
     Anſ
    -0.57
     "<?
    -0.57
     Biôgrafia
    -0.56
     Efq
    -0.56
     Signalez
    -0.56
    POSITIVE LOGITS
     
    0.58
    ca
    0.48
    BrowserModule
    0.47
    ed
    0.47
    تقاوى
    0.46
     téléchargez
    0.46
    XmlRootElement
    0.45
     than
    0.45
    aurais
    0.45
    WriteBarrier
    0.43
    Activations Density 0.004%

    No Known Activations