© 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. 4376
    Prev
    Next
    INDEX
    Explanations

    News, emails, and updates

    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
    ComponentName
    -0.46
    ']='
    -0.43
    rawtypes
    -0.42
     seams
    -0.42
     crows
    -0.41
     vian
    -0.41
    showroom
    -0.40
     Komplex
    -0.40
     metron
    -0.40
     hierarchy
    -0.39
    POSITIVE LOGITS
    posedge
    0.81
     Roskov
    0.66
     disambiguazione
    0.66
     незавершена
    0.62
     Never
    0.62
     Wicidata
    0.60
    Never
    0.60
    AndEndTag
    0.59
     Infórmanos
    0.57
    minecraftforge
    0.56
    Activations Density 0.000%

    No Known Activations