© 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. 1-CLT-HP
    7. 14408
    Prev
    Next
    INDEX
    Explanations

    prote

    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
    oprote
    -0.90
    \{\\
    -0.68
    पया
    -0.66
    HttpPut
    -0.60
    ReusableCell
    -0.60
     @"/
    -0.57
    ]")]
    -0.56
     propOrder
    -0.56
    ]`
    -0.56
     terroir
    -0.56
    POSITIVE LOGITS
    IntoConstraints
    0.56
    曖昧さ回避
    0.52
    ństwo
    0.49
    comune
    0.49
    inst
    0.48
     conséquence
    0.47
    conven
    0.47
     Meas
    0.47
     Carlsbad
    0.46
    ctives
    0.46
    Activations Density 0.014%

    No Known Activations