© 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. 0-CLT-HP
    7. 41515
    Prev
    Next
    INDEX
    Explanations

    described

    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
     described
    -1.63
    described
    -1.47
     describe
    -1.36
     descrito
    -1.31
     describes
    -1.28
     Described
    -1.27
     describing
    -1.13
     décrit
    -1.13
     describir
    -1.07
     DESCR
    -1.06
    POSITIVE LOGITS
     Anſ
    0.76
     reaſon
    0.69
    RunWith
    0.69
     purpoſe
    0.67
     Jefus
    0.67
     leaſt
    0.66
    onAttach
    0.66
     iſt
    0.65
     Cæsar
    0.65
     Efq
    0.65
    Activations Density 0.111%

    No Known Activations