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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5011
    Prev
    Next
    INDEX
    Explanations

    and

    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
    styleable
    -0.56
    jupiter
    -0.54
     welche
    -0.51
    ýt
    -0.50
     ubica
    -0.49
     which
    -0.48
    izoen
    -0.48
     internetowa
    -0.47
     telling
    -0.47
     implying
    -0.46
    POSITIVE LOGITS
     again
    0.66
    IsMutable
    0.65
    ]--;
    0.62
     Normdatei
    0.61
     насељу
    0.59
     ComVisible
    0.59
    HasForeignKey
    0.58
     uſed
    0.55
     novamente
    0.54
    )++;
    0.54
    Activations Density 0.003%

    No Known Activations