© 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. 20-CLT-HP
    7. 77429
    Prev
    Next
    INDEX
    Explanations

    Code and operating systems

    np_max-act-logits · 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
    ($__
    -0.65
    aways
    -0.63
     NOK
    -0.61
    eton
    -0.56
    icos
    -0.55
    惑
    -0.55
     kN
    -0.55
     Ensign
    -0.55
     timers
    -0.55
     acorn
    -0.55
    POSITIVE LOGITS
    aarrggbb
    0.57
    balleur
    0.51
    webElementXpaths
    0.47
     []:
    0.46
    ]")]
    0.42
    Externé
    0.42
     насељу
    0.42
    canestro
    0.41
    thâu
    0.41
    FieldBuilder
    0.41
    Activations Density 0.005%

    No Known Activations