© 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. 0-CLT-HP
    7. 94815
    Prev
    Next
    INDEX
    Explanations

    of

    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
     متعلقه
    -1.37
    AndEndTag
    -1.23
     autorytatywna
    -1.12
    featureID
    -1.05
     initComponents
    -1.05
     disambiguazione
    -1.05
    RectangleBorder
    -1.04
    ніципа
    -1.03
     Infórmanos
    -1.01
    SharedDtor
    -1.00
    POSITIVE LOGITS
     the
    0.58
     no
    0.54
     “
    0.52
    ,
    0.52
     over
    0.51
     in
    0.51
     to
    0.50
    <eos>
    0.49
     or
    0.49
     (
    0.49
    Activations Density 0.270%

    No Known Activations