© 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. 5598
    Prev
    Next
    INDEX
    Explanations

    charitable organizations and nonprofits

    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
     utafitiHapana
    -0.57
    Diweddarwch
    -0.51
     CanadaChoose
    -0.49
     ostavi
    -0.47
     nakalista
    -0.47
    صفات
    -0.45
    ี่ยน
    -0.45
     utenti
    -0.44
    AutoSize
    -0.44
     sách
    -0.44
    POSITIVE LOGITS
     organisations
    0.64
     work
    0.64
     raiſ
    0.64
    EndGlobalSection
    0.63
     colle
    0.63
     organizations
    0.62
     groups
    0.61
     MatDialog
    0.60
    ActionEvent
    0.60
     ſtate
    0.59
    Activations Density 0.000%

    No Known Activations