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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43151
    Prev
    Next
    INDEX
    Explanations

    data and explanations

    np_max-act · gemini-2.0-flash

    say "▁ (leading space)"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    __);
    -0.57
    __':
    -0.56
    MouseClicked
    -0.52
    __":
    -0.52
    }/{
    -0.51
    }")
    -0.51
    pegno
    -0.51
     []).
    -0.50
    >",
    -0.50
     AssemblyTitle
    -0.50
    POSITIVE LOGITS
    ंदीखरीदारी
    0.62
     beautiful
    0.59
     lovely
    0.59
     nice
    0.56
     super
    0.56
     amazing
    0.54
     terima
    0.54
     Super
    0.53
     good
    0.53
     gorgeous
    0.52
    Activations Density 0.011%

    No Known Activations