© 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. 20-CLT-HP
    7. 76131
    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
    DebuggerNonUser
    -0.76
     publicitaires
    -0.55
    MessageState
    -0.53
     bezeichneter
    -0.53
    zköz
    -0.53
    oredCriteria
    -0.52
     betweenstory
    -0.52
     Vader
    -0.50
    }$_
    -0.49
    suke
    -0.49
    POSITIVE LOGITS
     input
    0.54
     autorytatywna
    0.54
     inputs
    0.54
    plain
    0.52
     action
    0.52
    发表于
    0.51
     exchange
    0.51
     plumes
    0.50
    fed
    0.48
    허
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.