© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45381
    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
    曖昧さ回避
    -0.54
    قم
    -0.50
    Anonymous
    -0.47
    ]))
    -0.46
     nameless
    -0.45
    infer
    -0.45
     In
    -0.44
     Mous
    -0.43
     noise
    -0.43
    JsonIgnore
    -0.43
    POSITIVE LOGITS
    UIControlState
    0.83
     podjela
    0.67
    extAlignment
    0.63
    ReusableCell
    0.62
     Infórmanos
    0.61
     виправивши
    0.60
    lewati
    0.60
     Alamy
    0.60
    UpInside
    0.60
    TRAILING
    0.58
    Activations Density 0.690%

    No Known Activations