© 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. 14476
    Prev
    Next
    INDEX
    Explanations

    period

    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>
    -0.65
     propOrder
    -0.63
     jspb
    -0.60
     createSlice
    -0.60
    baomidou
    -0.59
    ↵↵
    -0.58
     A
    -0.58
    etCode
    -0.57
    msgSender
    -0.57
    FilterChain
    -0.57
    POSITIVE LOGITS
    ształ
    0.48
    bacter
    0.46
     spleen
    0.44
     fumig
    0.43
     fung
    0.42
    Ừ
    0.42
     fusca
    0.42
     fondue
    0.42
    Salmonella
    0.42
     acta
    0.41
    Activations Density 0.024%

    No Known Activations