© 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. 43929
    Prev
    Next
    INDEX
    Explanations

    medical treatments and phobias

    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
    исленность
    -1.16
     ་་
    -1.14
     bezeichneter
    -1.11
     Roskov
    -1.10
    ^(@)
    -1.09
     ―――――
    -1.09
     itſelf
    -1.09
     Efq
    -1.05
     XNUMX
    -1.03
     Theſe
    -1.03
    POSITIVE LOGITS
     pro
    0.51
    T
    0.51
    hen
    0.49
    <em>
    0.49
     ag
    0.49
    I
    0.49
    app
    0.48
     I
    0.47
     app
    0.47
    S
    0.47
    Activations Density 0.199%

    No Known Activations