© 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. 97774
    Prev
    Next
    INDEX
    Explanations

    locations and surroundings

    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
    siana
    -0.53
    ArgsConstructor
    -0.52
    SizeMode
    -0.51
    NamedQuery
    -0.50
     beauty
    -0.49
    viewDidLoad
    -0.47
     fresh
    -0.47
    CloseOperation
    -0.46
    StoryboardSegue
    -0.46
    GIVEREF
    -0.44
    POSITIVE LOGITS
     us
    0.82
     me
    0.75
     aisladas
    0.64
     you
    0.62
    LLocation
    0.62
     racines
    0.60
     bénévoles
    0.59
     inconvénients
    0.59
     chrétiens
    0.59
     ouvriers
    0.59
    Activations Density 0.006%

    No Known Activations