© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11678
    Prev
    Next
    INDEX
    Explanations

    canal

    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
    windowFixed
    -0.68
    OGND
    -0.66
     Bourgoin
    -0.61
    InjectAttribute
    -0.59
     étrangères
    -0.57
    ecore
    -0.57
     épis
    -0.56
    oa̍t
    -0.54
     pleaſure
    -0.53
    FunctionFlags
    -0.52
    POSITIVE LOGITS
     StringTokenizer
    0.50
     beat
    0.45
     crop
    0.45
    σμο
    0.44
    """,
    0.43
    jka
    0.43
    principalTable
    0.43
    @",
    0.43
     wind
    0.42
     rip
    0.42
    Activations Density 0.064%

    No Known Activations