© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5141
    Prev
    Next
    INDEX
    Explanations

    a

    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
    onames
    -0.50
    AndPassword
    -0.45
     eventdata
    -0.44
     lần
    -0.43
    gifs
    -0.42
    stdc
    -0.42
    foria
    -0.42
    pubs
    -0.40
    here
    -0.40
    tvguidetime
    -0.40
    POSITIVE LOGITS
    })`
    0.65
    ]='\
    0.63
     ProtoMessage
    0.63
     houſe
    0.63
     ſmall
    0.61
    SourceChecksum
    0.61
     faſt
    0.60
     smaller
    0.60
     leſs
    0.60
     simpler
    0.60
    Activations Density 0.004%

    No Known Activations