© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94953
    Prev
    Next
    INDEX
    Explanations

    :

    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
    Ecotoxicity
    -0.57
     dikutip
    -0.57
     Romains
    -0.56
    gnancy
    -0.55
     we
    -0.55
    abetes
    -0.52
     pleaſure
    -0.52
    rinology
    -0.52
     open
    -0.52
     inner
    -0.52
    POSITIVE LOGITS
     estimés
    0.70
    +#+
    0.57
     pyplot
    0.56
    DoubleQuotes
    0.53
    forRoot
    0.52
    #+#
    0.49
    capulco
    0.49
     surla
    0.48
    pyplot
    0.47
    AccessorTable
    0.47
    Activations Density 0.001%

    No Known Activations