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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 678
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    憑
    -0.55
    )?;
    -0.52
    σκε
    -0.51
    )}>
    -0.51
    matchCondition
    -0.51
     }}</
    -0.51
    dafx
    -0.51
    "]))
    -0.50
    ")))
    -0.50
    ratic
    -0.50
    POSITIVE LOGITS
    VolleyError
    0.64
     GenerationType
    0.60
    ApiModelProperty
    0.49
    rungsseite
    0.49
     initComponents
    0.49
     morts
    0.48
     Fracture
    0.48
    ftagPool
    0.48
    enumi
    0.48
     dermatologist
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.