© 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. 92602
    Prev
    Next
    INDEX
    Explanations

    fair

    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
    Datuak
    -0.81
    BeginContext
    -0.73
    webElementXpaths
    -0.70
    setVerticalGroup
    -0.64
     AssemblyTitle
    -0.62
     microm
    -0.62
     TestBed
    -0.61
     pyr
    -0.60
     paid
    -0.59
    StoryboardSegue
    -0.59
    POSITIVE LOGITS
     océ
    0.49
    hilation
    0.46
     оригіналу
    0.46
    +#+#
    0.43
     otomatig
    0.39
    conservation
    0.39
     hallaz
    0.39
     féd
    0.39
     metav
    0.38
    tapeta
    0.38
    Activations Density 0.000%

    No Known Activations