© 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. 43089
    Prev
    Next
    INDEX
    Explanations

    monomer

    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
     vérit
    -0.94
    ChildScrollView
    -0.89
     vectorielles
    -0.89
     preuves
    -0.85
     résine
    -0.82
     cérami
    -0.82
     motivadoras
    -0.81
     mauva
    -0.81
     intérieure
    -0.81
     étoient
    -0.81
    POSITIVE LOGITS
    ings
    0.70
    ish
    0.62
    ies
    0.53
    here
    0.49
    er
    0.48
    ized
    0.47
    ries
    0.46
    ize
    0.45
    ization
    0.45
    isation
    0.45
    Activations Density 0.044%

    No Known Activations