© 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. 1-CLT-HP
    7. 9705
    Prev
    Next
    INDEX
    Explanations

    hold

    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
     hold
    -0.95
    hold
    -0.90
     held
    -0.84
     Hold
    -0.80
    Hold
    -0.79
     holds
    -0.79
     holding
    -0.74
     Holds
    -0.74
    HOLD
    -0.73
     HOLD
    -0.69
    POSITIVE LOGITS
    IntoConstraints
    0.65
    \|_{\
    0.63
     createState
    0.61
    KURZBESCHREIBUNG
    0.60
    makeConstraints
    0.58
     invokingState
    0.53
     contextLoads
    0.50
     doInBackground
    0.50
     InputDecoration
    0.50
     numerus
    0.50
    Activations Density 0.030%

    No Known Activations