© 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. 5818
    Prev
    Next
    INDEX
    Explanations

    Names and history

    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
     betweenstory
    -0.53
    verifyException
    -0.52
    remel
    -0.50
    caped
    -0.48
    ParseTree
    -0.48
    ِّف
    -0.47
    ParallelGroup
    -0.47
     app
    -0.46
    WebElementEntity
    -0.46
    retz
    -0.46
    POSITIVE LOGITS
    ]")]
    0.61
     Waray
    0.57
    IndentedString
    0.56
    BagConstraints
    0.56
    heads
    0.56
    يات
    0.53
     conduc
    0.53
     utafitiHapana
    0.52
     Normdatei
    0.49
     vokal
    0.49
    Activations Density 0.003%

    No Known Activations