© 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. 45973
    Prev
    Next
    INDEX
    Explanations

    frame

    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
     framing
    -1.34
     frame
    -1.25
     Framing
    -1.23
    framing
    -1.20
    Frame
    -1.19
     frames
    -1.17
    frame
    -1.16
     Frame
    -1.13
     Frames
    -1.11
    frames
    -1.10
    POSITIVE LOGITS
    EndInit
    0.80
    ParallelGroup
    0.71
    ScopeManager
    0.63
    enumi
    0.62
    躇
    0.60
     Lockhart
    0.60
    paksa
    0.60
     IOError
    0.59
     vuitton
    0.59
    moires
    0.59
    Activations Density 0.007%

    No Known Activations