© 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. 0-CLT-HP
    7. 91116
    Prev
    Next
    INDEX
    Explanations

    amplifier

    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
     amp
    -1.73
     Amp
    -1.69
    Amp
    -1.66
     amplifiers
    -1.59
     amplification
    -1.48
    amp
    -1.47
     amplifier
    -1.47
     amplify
    -1.47
     amps
    -1.46
     amplified
    -1.44
    POSITIVE LOGITS
    t
    0.65
    as
    0.61
    y
    0.57
    at
    0.56
    ят
    0.52
    u
    0.52
    ed
    0.51
    e
    0.51
    i
    0.50
    an
    0.48
    Activations Density 0.432%

    No Known Activations