© 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. 4430
    Prev
    Next
    INDEX
    Explanations

    past

    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
     past
    -0.88
    historical
    -0.79
    past
    -0.77
     Historical
    -0.76
     historical
    -0.76
    Historical
    -0.75
     history
    -0.74
    history
    -0.71
     Past
    -0.71
     current
    -0.69
    POSITIVE LOGITS
    WebVitals
    0.89
     Houſe
    0.67
    PullParser
    0.65
    yled
    0.61
    NUMX
    0.60
     Efq
    0.59
    bernate
    0.59
     chaleur
    0.58
     doubtnut
    0.57
     estimés
    0.57
    Activations Density 0.001%

    No Known Activations