© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3890
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
    DebuggerNonUser
    -0.65
    WebVitals
    -0.61
    AsStream
    -0.49
     tartalomajánló
    -0.49
     onCancelled
    -0.45
     оригіналу
    -0.45
    ay
    -0.44
     Blame
    -0.44
    rativa
    -0.43
     MenuView
    -0.43
    POSITIVE LOGITS
     Réponses
    0.65
    ⓧ
    0.63
    +#+#
    0.57
    ########.
    0.52
     ligiloj
    0.52
    NameInMap
    0.51
    릅
    0.50
     >=",
    0.49
     contempt
    0.49
     casó
    0.49
    Activations Density 0.009%

    No Known Activations