© 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. 5-CLT-HP
    7. 92491
    Prev
    Next
    INDEX
    Explanations

    to

    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
     فريبيس
    -0.68
     %>%
    -0.50
    </thead>
    -0.49
     "":
    -0.48
     transfieras
    -0.48
     brilli
    -0.47
    saraba
    -0.47
     posX
    -0.47
    umph
    -0.46
    '`
    -0.46
    POSITIVE LOGITS
     the
    0.73
     using
    0.59
     having
    0.58
    extAlignment
    0.57
     Möglich
    0.57
    AsUp
    0.56
     getting
    0.55
     installing
    0.55
     choosing
    0.54
     submitting
    0.54
    Activations Density 0.001%

    No Known Activations