© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5986
    Prev
    Next
    INDEX
    Explanations

    time

    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
     revés
    -0.58
     femininas
    -0.50
    whereas
    -0.47
    στό
    -0.47
    </caption>
    -0.47
     surla
    -0.47
    ztyn
    -0.45
    abord
    -0.45
    @[+][
    -0.45
    MessageState
    -0.44
    POSITIVE LOGITS
     I
    1.06
     we
    0.81
     anyone
    0.73
     my
    0.69
     someone
    0.65
     qualquer
    0.59
     anybody
    0.59
     any
    0.57
     he
    0.56
    ://
    0.55
    Activations Density 0.012%

    No Known Activations