© 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. 0-CLT-HP
    7. 45374
    Prev
    Next
    INDEX
    Explanations

    undetermined

    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
    classified
    -0.71
    msgSender
    -0.60
     unspecified
    -0.60
    e
    -0.60
     unclear
    -0.57
     Stevenson
    -0.55
    reactstrap
    -0.53
    uidado
    -0.52
    PRWEB
    -0.51
    ToolStripButton
    -0.51
    POSITIVE LOGITS
     propof
    0.64
     thermoc
    0.59
     nakalista
    0.56
    RectangleBorder
    0.55
     craters
    0.55
     Aper
    0.54
    اریخ
    0.53
     Aler
    0.52
    MessageState
    0.52
     astring
    0.52
    Activations Density 0.102%

    No Known Activations