Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4293
    Prev
    Next
    INDEX
    Explanations

    gentler

    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
    BeginContext
    -0.55
    unhofer
    -0.50
    $_['
    -0.46
     LCCN
    -0.45
    sud
    -0.44
     endwhile
    -0.42
     odkazy
    -0.41
     ymm
    -0.40
     Merz
    -0.40
     sister
    -0.40
    POSITIVE LOGITS
     bonnes
    0.59
    matchCondition
    0.59
    setVerticalGroup
    0.57
     hemsida
    0.56
    Solid
    0.56
     fondament
    0.55
     jeunes
    0.54
     verksamhet
    0.54
    tagHelperRunner
    0.53
     positifs
    0.53
    Activations Density 0.002%

    No Known Activations