© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45135
    Prev
    Next
    INDEX
    Explanations

    when

    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
    endphp
    -0.63
    <bos>
    -0.63
    databind
    -0.61
     Autorizaciones
    -0.58
    NewUrlParser
    -0.58
     when
    -0.57
    openqa
    -0.55
    học
    -0.54
    styleable
    -0.53
     typelib
    -0.52
    POSITIVE LOGITS
     springfox
    0.66
     sequestration
    0.59
    contentLoaded
    0.58
    1
    0.57
    AddRange
    0.56
    printStackTrace
    0.55
     Consolidated
    0.54
    4
    0.54
     condensation
    0.54
     mineralization
    0.54
    Activations Density 0.178%

    No Known Activations