© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 589
    Prev
    Next
    INDEX
    Explanations

    premises

    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
     premises
    -2.30
    premises
    -2.00
     Premises
    -1.91
     premise
    -1.68
    premise
    -1.46
    Premise
    -1.41
    mises
    -0.96
    mise
    -0.84
     prem
    -0.67
    prem
    -0.63
    POSITIVE LOGITS
     JpaRepository
    0.56
    withIdentifier
    0.54
    schirm
    0.53
    ัติ
    0.53
    存于互联网档案馆
    0.52
    saraba
    0.52
    +:+
    0.51
    Tikang
    0.51
    Expedia
    0.51
    RunWith
    0.50
    Activations Density 0.017%

    No Known Activations