© 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. 6058
    Prev
    Next
    INDEX
    Explanations

    3

    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
    Negative Logits
    #+#
    -0.59
    AnchorStyles
    -0.52
     تضيفلها
    -0.51
     estekak
    -0.49
    StoryboardSegue
    -0.48
    ChildIndex
    -0.47
    +#+
    -0.45
    astéro
    -0.45
    DialogContent
    -0.44
    ropoda
    -0.44
    POSITIVE LOGITS
    swig
    0.61
    qtype
    0.57
     exemples
    0.57
     dichiarato
    0.54
    Przypisy
    0.52
     of
    0.52
     PyQt
    0.50
    tldr
    0.50
     jLabel
    0.50
     <<<<<<<<<<<<<<
    0.50
    Activations Density 0.001%

    No Known Activations