© 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. 92706
    Prev
    Next
    INDEX
    Explanations

    Linguistics/grammar

    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
    onAttach
    -0.60
    StoryboardSegue
    -0.57
    fvar
    -0.52
     onCreateView
    -0.51
     препратки
    -0.50
    #+#
    -0.49
     uncompromising
    -0.49
     تضيفلها
    -0.48
     Gemeinsame
    -0.48
    invokeLater
    -0.47
    POSITIVE LOGITS
     colonnes
    0.67
    thâu
    0.65
    cellona
    0.65
     symboles
    0.61
    VersionUID
    0.60
     compresión
    0.60
    ulement
    0.59
     journaux
    0.58
     térm
    0.58
     pério
    0.58
    Activations Density 0.001%

    No Known Activations