© 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. 97602
    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
    orph
    -1.25
    !*\
    -0.54
    ParallelGroup
    -0.47
     refaire
    -0.47
    дото
    -0.45
     Réponses
    -0.45
    setType
    -0.45
     giustizia
    -0.44
     nutzt
    -0.43
    tinyos
    -0.42
    POSITIVE LOGITS
    InputBorder
    0.77
    VersionUID
    0.77
    IntoConstraints
    0.74
     endwhile
    0.62
    存于互联网档案馆
    0.60
     CWE
    0.59
    SOUNDBITE
    0.59
    LoadScene
    0.59
    Демографія
    0.58
    HasAnnotation
    0.58
    Activations Density 0.703%

    No Known Activations