© 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. 5-CLT-HP
    7. 96816
    Prev
    Next
    INDEX
    Explanations

    home

    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
    ze
    -0.45
    lee
    -0.45
    <?
    -0.44
    }}}$
    -0.43
    pu
    -0.43
    ime
    -0.43
    moor
    -0.42
    une
    -0.42
    i
    -0.42
    ik
    -0.41
    POSITIVE LOGITS
     or
    0.77
     виправивши
    0.75
     تضيفلها
    0.71
     createSlice
    0.69
    resents
    0.67
    mistry
    0.66
    ЧИТА
    0.64
    ByVersion
    0.64
    Портал
    0.63
    Geplaatst
    0.63
    Activations Density 0.000%

    No Known Activations