© 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. 2008
    Prev
    Next
    INDEX
    Explanations

    account

    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
    SqlClient
    -0.64
    IndentedString
    -0.62
    )}</
    -0.61
    sidemargin
    -0.60
    ENIX
    -0.60
    出版年
    -0.59
    ')")
    -0.58
    uously
    -0.57
     degradability
    -0.57
    ध्य
    -0.57
    POSITIVE LOGITS
    ďaka
    0.56
     gouttes
    0.54
     huiles
    0.54
     mourut
    0.52
    Set
    0.52
     espagne
    0.51
     essentielles
    0.51
     gynhyrchwyd
    0.51
     particulières
    0.51
     détach
    0.50
    Activations Density 0.001%

    No Known Activations