© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96715
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     something
    -1.06
    something
    -0.91
     Something
    -0.90
     ModelExpression
    -0.86
     SOMETHING
    -0.85
     somethin
    -0.82
    Something
    -0.81
     qualcosa
    -0.77
     coś
    -0.75
     hump
    -0.74
    POSITIVE LOGITS
    TagMode
    0.75
    ))]
    0.47
    )』
    0.44
    adpleegd
    0.43
     weiterer
    0.43
    :
    0.42
    ]")]
    0.42
     that
    0.42
    stdbool
    0.42
    newtheorem
    0.41
    Activations Density 0.002%

    No Known Activations