© 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. 14966
    Prev
    Next
    INDEX
    Explanations

    make

    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
    ImageContext
    -0.70
    matchCondition
    -0.68
    SourceChecksum
    -0.66
     CreateTagHelper
    -0.66
    <bos>
    -0.64
    addPreferredGap
    -0.62
     StringTokenizer
    -0.61
    Datuak
    -0.60
    styleType
    -0.60
    irical
    -0.60
    POSITIVE LOGITS
    rinus
    0.46
     Williams
    0.46
    grip
    0.45
    "?>
    0.44
    Masukkan
    0.43
    emark
    0.41
    Propel
    0.41
    plash
    0.41
    pulumi
    0.41
    )\}
    0.41
    Activations Density 0.004%

    No Known Activations