© 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. 4-CLT-HP
    7. 836
    Prev
    Next
    INDEX
    Explanations

    June

    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
     the
    -0.87
     your
    -0.77
    the
    -0.63
     purpoſe
    -0.59
     YOUR
    -0.58
     this
    -0.58
     Cæsar
    -0.56
     pleaſure
    -0.56
     onCancelled
    -0.55
     someone
    -0.55
    POSITIVE LOGITS
    发表于
    0.53
     MotionEvent
    0.48
     continúas
    0.47
    MigrationBuilder
    0.47
    #+#
    0.46
     gezogen
    0.45
    所以我
    0.45
    /**
    0.44
    Externé
    0.44
    :^(
    0.43
    Activations Density 0.004%

    No Known Activations