© 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. 2529
    Prev
    Next
    INDEX
    Explanations

    to

    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
    öße
    -0.56
    ताब
    -0.46
    IActionResult
    -0.45
    från
    -0.44
    UnknownFields
    -0.44
    strokeStyle
    -0.43
    vily
    -0.42
    שְׁ
    -0.41
    SOUNDBITE
    -0.41
     flesta
    -0.41
    POSITIVE LOGITS
     the
    1.09
     how
    0.73
    }/${
    0.71
    onAttach
    0.67
    ])[
    0.65
    LookAnd
    0.64
     OFDb
    0.62
     just
    0.61
    ])/
    0.60
    GraphicsUnit
    0.58
    Activations Density 0.000%

    No Known Activations