© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 97491
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
     للاسماء
    -0.82
    ]")]
    -0.80
     متعلقه
    -0.77
    parsedMessage
    -0.77
    '}),
    -0.76
    )"),
    -0.74
    ).]
    -0.72
    }}],
    -0.71
    rungsseite
    -0.71
    jsonwebtoken
    -0.71
    POSITIVE LOGITS
     tiny
    0.43
    localScale
    0.41
     colourless
    0.40
     picioare
    0.39
    رز
    0.39
     Raman
    0.39
     "
    0.37
    ほうが
    0.36
     malle
    0.36
     piele
    0.36
    Activations Density 0.145%

    No Known Activations