© 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. 4577
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    Personendaten
    -0.70
    parsedMessage
    -0.68
     كومونز
    -0.65
     kaarangay
    -0.60
     незавершена
    -0.55
     exploiting
    -0.55
     using
    -0.52
    StructEnd
    -0.52
     that
    -0.51
    IntoConstraints
    -0.50
    POSITIVE LOGITS
    PYX
    0.47
     lenker
    0.47
    houn
    0.47
    moveToFirst
    0.45
     (!_
    0.45
     denote
    0.45
     ldc
    0.45
    wicket
    0.45
    setopt
    0.45
     MotionEvent
    0.44
    Activations Density 0.087%

    No Known Activations