© 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. 1-CLT-HP
    7. 46185
    Prev
    Next
    INDEX
    Explanations

    retreat

    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
     Reusable
    -0.45
     reusable
    -0.45
     Gor
    -0.43
     Ban
    -0.42
     ř
    -0.41
    Ban
    -0.41
     fianco
    -0.40
     bArr
    -0.40
    ef
    -0.40
    element
    -0.40
    POSITIVE LOGITS
     houſe
    0.82
     purpoſe
    0.75
    الدراسه
    0.75
     ſta
    0.75
     Jefus
    0.74
     myſelf
    0.73
     contextLoads
    0.73
     Houſe
    0.71
    }")]
    0.71
     itſelf
    0.71
    Activations Density 0.009%

    No Known Activations