© 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. 92189
    Prev
    Next
    INDEX
    Explanations

    {

    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
    rungsseite
    -0.70
     autorytatywna
    -0.70
    IUrlHelper
    -0.65
    الإنجليزية
    -0.63
    Huile
    -0.59
     contextLoads
    -0.55
    fibra
    -0.54
    tichetta
    -0.54
    èdia
    -0.53
     hanem
    -0.52
    POSITIVE LOGITS
    __':
    0.65
    ()])
    0.57
    Getenv
    0.55
    __':
    0.52
     exact
    0.51
    AnchorTagHelper
    0.50
    Vanjske
    0.49
     Orrell
    0.48
    ()]
    0.48
     policing
    0.48
    Activations Density 2.302%

    No Known Activations