© 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. 20-CLT-HP
    7. 73256
    Prev
    Next
    INDEX
    Explanations

    Air

    np_max-act-logits · 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
    jspx
    -0.73
    Personensuche
    -0.58
    WebElementEntity
    -0.56
    Controllo
    -0.56
     الرياضيه
    -0.56
     Devonian
    -0.55
    wahati
    -0.54
     informée
    -0.53
    AutoScaleMode
    -0.52
     noDo
    -0.52
    POSITIVE LOGITS
    TestBed
    0.54
     محفوظة
    0.51
     Gesch
    0.51
    :]:
    0.48
     وابسته
    0.47
    }`,
    0.46
    temper
    0.46
    AddressBook
    0.45
    dération
    0.44
    Snoo
    0.43
    Activations Density 0.001%

    No Known Activations