© 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. 0-CLT-HP
    4. 1673
    Prev
    Next
    INDEX
    Explanations

    self

    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
     self
    -1.26
     Self
    -1.17
    Self
    -1.05
    self
    -0.78
     SELF
    -0.75
     Selbst
    -0.63
    SELF
    -0.60
    自
    -0.56
    自我
    -0.54
     The
    -0.52
    POSITIVE LOGITS
     myſelf
    1.17
     iſt
    1.08
     Efq
    1.08
     Theſe
    1.06
     Jefus
    1.04
    principalColumn
    1.02
     pleaſure
    1.02
     Monfieur
    1.02
     ſtre
    1.01
     deſt
    1.01
    Activations Density 0.173%

    No Known Activations