© 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. 5542
    Prev
    Next
    INDEX
    Explanations

    about

    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
     betweenstory
    -0.75
    المكان
    -0.68
     صوتيه
    -0.65
    ᅠ
    -0.65
    Personensuche
    -0.65
    Попис
    -0.65
     apellidos
    -0.64
    FieldNumber
    -0.63
     gainera
    -0.63
    orianCalendar
    -0.60
    POSITIVE LOGITS
     how
    0.71
     long
    0.61
     rechange
    0.61
    -------
    0.56
     cuándo
    0.48
     when
    0.47
     følger
    0.46
     longer
    0.45
    OTES
    0.45
     sonra
    0.43
    Activations Density 0.001%

    No Known Activations