© 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. 5-CLT-HP
    7. 96219
    Prev
    Next
    INDEX
    Explanations

    necessity

    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
     slik
    -0.47
     To
    -0.47
     Alternative
    -0.46
    اب
    -0.45
    相
    -0.44
     Leit
    -0.43
     From
    -0.42
     to
    -0.42
     saites
    -0.42
    寸
    -0.42
    POSITIVE LOGITS
    SBATCH
    0.83
     unless
    0.77
    脚注の使い方
    0.77
     يتيمه
    0.71
    InputBorder
    0.70
     dacă
    0.67
    unless
    0.66
    Obrázky
    0.65
     autorytatywna
    0.62
     ikiwa
    0.62
    Activations Density 0.001%

    No Known Activations