© 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. 39883
    Prev
    Next
    INDEX
    Explanations

    bracket

    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
    getItemId
    -0.50
    lian
    -0.49
     Easy
    -0.47
    \|_{\
    -0.47
    ross
    -0.46
     <!--
    -0.45
    DoubleQuotes
    -0.45
     easy
    -0.44
     Aktion
    -0.44
    )|^{
    -0.44
    POSITIVE LOGITS
    +#+#
    0.92
    ########.
    0.77
     يتيمه
    0.72
    fromnode
    0.63
    SequentialGroup
    0.63
    loem
    0.63
    terapia
    0.62
     createState
    0.61
     Públicas
    0.61
     frontale
    0.60
    Activations Density 1.645%

    No Known Activations