© 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. 97796
    Prev
    Next
    INDEX
    Explanations

    circumstances

    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
     myſelf
    -0.73
     tartalomajánló
    -0.67
     themſelves
    -0.66
    сылкі
    -0.66
     houſe
    -0.65
     Jefus
    -0.65
    цездатний
    -0.64
     iſt
    -0.63
     itſelf
    -0.61
    hoeddwyd
    -0.61
    POSITIVE LOGITS
     שוליים
    0.65
     encountered
    0.57
     situation
    0.52
     involving
    0.50
     scenario
    0.50
     faced
    0.49
     facing
    0.47
     situação
    0.47
     requiring
    0.46
     handled
    0.46
    Activations Density 0.002%

    No Known Activations