© 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. 10317
    Prev
    Next
    INDEX
    Explanations

    children

    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
    contentLoaded
    -0.87
     ivelany
    -0.71
    TagHelper
    -0.69
    ftagPool
    -0.65
    Chham
    -0.65
    StructEnd
    -0.63
    osoba
    -0.62
    UNRELATED
    -0.60
    GIVEREF
    -0.59
     صوتيه
    -0.59
    POSITIVE LOGITS
    ChildScrollView
    0.53
     يتيمه
    0.50
    IBOutlet
    0.49
     direct
    0.46
     CL
    0.43
    বে
    0.42
    <bos>
    0.41
     Cio
    0.41
    cracker
    0.41
    croll
    0.41
    Activations Density 0.003%

    No Known Activations