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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97368
    Prev
    Next
    INDEX
    Explanations

    debilitating

    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
    theon
    -0.65
    ly
    -0.62
     aikaa
    -0.59
    yntaxException
    -0.58
     initComponents
    -0.58
    mtable
    -0.57
     Mondiale
    -0.57
    fully
    -0.56
    ruptcy
    -0.56
    grees
    -0.56
    POSITIVE LOGITS
    ########.
    0.62
    tvguidetime
    0.62
    BASEPATH
    0.59
    KURZBESCHREIBUNG
    0.58
    +#+#
    0.54
    \[\
    0.52
    haut
    0.52
    Initializable
    0.52
     '=',
    0.51
    ibatis
    0.49
    Activations Density 0.110%

    No Known Activations