© 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. 0-CLT-HP
    7. 41393
    Prev
    Next
    INDEX
    Explanations

    distance

    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
     mile
    -2.52
     miles
    -2.27
    mile
    -2.27
    miles
    -2.02
    Mile
    -2.00
     Mile
    -1.93
     MILE
    -1.84
     MILES
    -1.72
     Miles
    -1.65
    Miles
    -1.63
    POSITIVE LOGITS
    2
    0.61
    0
    0.59
    .
    0.56
    3
    0.54
    7
    0.53
    h
    0.53
    1
    0.52
    5
    0.52
    6
    0.51
    ep
    0.51
    Activations Density 0.169%

    No Known Activations