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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 446
    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
    frame
    -1.28
    frames
    -1.20
     frame
    -1.18
     frames
    -1.18
    Frame
    -1.06
     Frame
    -1.05
    FRAME
    -1.02
     FRAME
    -0.96
    framing
    -0.96
     framing
    -0.94
    POSITIVE LOGITS
    berdayakan
    0.60
     Caballero
    0.54
    SourceChecksum
    0.53
     Gegenteil
    0.53
     }}"></
    0.52
     anecdotal
    0.52
     berisi
    0.51
    Cyfarwyddwr
    0.51
    jalá
    0.51
    Портал
    0.51
    Activations Density 0.278%

    No Known Activations