© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1160
    Prev
    Next
    INDEX
    Explanations

    Times

    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
    SequentialGroup
    -0.56
    featureID
    -0.48
    imler
    -0.46
    Jac
    -0.43
     Jac
    -0.43
    OwnProperty
    -0.43
    fillType
    -0.42
    DialogInterface
    -0.42
     olduk
    -0.42
    uração
    -0.41
    POSITIVE LOGITS
     betweenstory
    0.72
     MainAxisSize
    0.64
    Rohy
    0.62
    RenderAtEndOf
    0.59
    resave
    0.59
     utafitiHapana
    0.56
     metav
    0.56
    
    0.56
     Chwiliwch
    0.56
    extField
    0.54
    Activations Density 0.004%

    No Known Activations