© 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. 4824
    Prev
    Next
    INDEX
    Explanations

    looking

    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
    archiviato
    -0.52
     behulp
    -0.52
     CreateTagHelper
    -0.51
     remonter
    -0.50
    المشاركات
    -0.48
     of
    -0.48
     from
    -0.47
     on
    -0.47
    setViewportView
    -0.47
     souhait
    -0.46
    POSITIVE LOGITS
     Normdatei
    0.87
    Autoritní
    0.71
    uttavia
    0.62
     nahilalakip
    0.60
    tedly
    0.59
    SBATCH
    0.59
     autorytatywna
    0.58
     passage
    0.58
    őtt
    0.57
     but
    0.56
    Activations Density 0.004%

    No Known Activations