© 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. 0-CLT-HP
    7. 43625
    Prev
    Next
    INDEX
    Explanations

    arrives

    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
     arrives
    -1.12
     arrived
    -1.10
     arrive
    -1.07
    mal
    -1.05
     mal
    -1.00
     comes
    -0.94
     arriving
    -0.91
     Mal
    -0.86
    Mal
    -0.82
    comes
    -0.79
    POSITIVE LOGITS
     purpoſe
    0.86
     متعلقه
    0.84
     poffible
    0.81
     raiſ
    0.79
     ſever
    0.76
     faſt
    0.76
     Majefty
    0.75
     houſe
    0.74
     ſche
    0.73
     ſeveral
    0.73
    Activations Density 0.082%

    No Known Activations