© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12097
    Prev
    Next
    INDEX
    Explanations

    protein

    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
    <bos>
    -0.49
     female
    -0.44
    AddRange
    -0.42
    onas
    -0.40
     chè
    -0.39
     mergeFrom
    -0.39
    onic
    -0.38
    DrawerToggle
    -0.37
    idon
    -0.37
     button
    -0.37
    POSITIVE LOGITS
    InputTagHelper
    0.67
    CodedInputStream
    0.66
    WebVitals
    0.65
    sidemargin
    0.63
    nestjs
    0.63
     Himo
    0.63
     distanciation
    0.61
    SerializedName
    0.60
    AndEndTag
    0.60
     ligiloj
    0.59
    Activations Density 0.039%

    No Known Activations