© 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. 1-CLT-HP
    7. 10138
    Prev
    Next
    INDEX
    Explanations

    h

    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
    alpin
    -0.51
     ent
    -0.48
     honor
    -0.47
    ọi
    -0.47
    owskiego
    -0.46
     sé
    -0.46
    Lastname
    -0.45
    λο
    -0.45
     honored
    -0.44
     sorte
    -0.43
    POSITIVE LOGITS
     समीक्षक
    0.74
    tvguidetime
    0.71
     Италијани
    0.70
    expandindo
    0.67
    AnchorStyles
    0.66
     صوتيه
    0.65
     utafitiHapana
    0.65
    PRNewswire
    0.62
    oredCriteria
    0.62
    AutoScaleMode
    0.60
    Activations Density 0.237%

    No Known Activations