© 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. 91796
    Prev
    Next
    INDEX
    Explanations

    and, comma

    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
     autorytatywna
    -0.69
     automatiques
    -0.67
    Démographie
    -0.63
    Према
    -0.63
     Efq
    -0.61
     utafitiHapana
    -0.60
     mourut
    -0.59
    üyada
    -0.58
     táctil
    -0.57
     Majefty
    -0.57
    POSITIVE LOGITS
     heavily
    0.47
    pleft
    0.46
    Slight
    0.46
     redistribute
    0.45
    voyer
    0.45
    hlor
    0.44
     SIGNAL
    0.44
     tale
    0.44
     signal
    0.43
     taget
    0.43
    Activations Density 0.006%

    No Known Activations