© 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. 45937
    Prev
    Next
    INDEX
    Explanations

    hoo

    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
     незавершена
    -0.58
    ystis
    -0.55
     esquecer
    -0.54
     étoient
    -0.52
     définiti
    -0.52
    zeiten
    -0.52
     déput
    -0.52
     preocupes
    -0.51
     avoient
    -0.49
    cagon
    -0.49
    POSITIVE LOGITS
    Demografie
    0.63
    UnknownFields
    0.60
    <bos>
    0.58
    FunctionFlags
    0.58
    EditorBrowsable
    0.56
    nocache
    0.55
    NullCheck
    0.55
     force
    0.54
    Referències
    0.54
    原始内容存档于
    0.54
    Activations Density 0.036%

    No Known Activations