© 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. 92670
    Prev
    Next
    INDEX
    Explanations

    diagnosis

    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
    ņš
    -0.52
    SPATH
    -0.52
    voyez
    -0.47
     hende
    -0.46
    RequestQueue
    -0.46
    ſelves
    -0.46
    èrement
    -0.46
    UserScript
    -0.45
    InThe
    -0.45
    nehå
    -0.44
    POSITIVE LOGITS
    fromnode
    0.67
     indisponible
    0.57
    gulier
    0.53
    SpringRunner
    0.53
     betweenstory
    0.52
     letter
    0.52
    HttpDelete
    0.52
    epiece
    0.51
    عنی
    0.50
    prnewswire
    0.50
    Activations Density 0.003%

    No Known Activations