© 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. 92085
    Prev
    Next
    INDEX
    Explanations

    progressive

    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
     noDo
    -0.74
    AutoScaleMode
    -0.69
    IUrlHelper
    -0.69
     betweenstory
    -0.68
    tagHelperRunner
    -0.63
     cherchés
    -0.59
     snippetHide
    -0.59
    IVEREF
    -0.59
    routeProvider
    -0.57
     disambiguazione
    -0.57
    POSITIVE LOGITS
    Normdaten
    0.60
     to
    0.60
     plaque
    0.57
    llary
    0.56
     spontaneous
    0.54
     febri
    0.53
    govine
    0.53
     plaques
    0.52
    specific
    0.49
     protoimpl
    0.49
    Activations Density 0.916%

    No Known Activations