© 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. 1-CLT-HP
    7. 14533
    Prev
    Next
    INDEX
    Explanations

    bark

    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
    uta
    -0.72
    Bark
    -0.68
     barking
    -0.60
    ezers
    -0.59
    ējās
    -0.57
    üe
    -0.56
    UTED
    -0.56
    hematical
    -0.56
    licted
    -0.54
    GeneratedMessage
    -0.54
    POSITIVE LOGITS
    styleType
    0.61
    withIdentifier
    0.49
    HasMaxLength
    0.48
     estekak
    0.48
    <bos>
    0.47
    ChildScrollView
    0.46
     بيها
    0.46
    GEBURTSDATUM
    0.46
     كومونز
    0.44
     jazdy
    0.43
    Activations Density 0.073%

    No Known Activations