© 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. 1-CLT-HP
    7. 10630
    Prev
    Next
    INDEX
    Explanations

    God

    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
    GEBURTSDATUM
    -0.76
    MLLoader
    -0.71
     snippetHide
    -0.71
     newOwner
    -0.70
    DIPSETTING
    -0.69
    XmlAccessType
    -0.69
    TagMode
    -0.66
     createSlice
    -0.65
    IntoConstraints
    -0.64
    findpost
    -0.63
    POSITIVE LOGITS
    一行
    0.55
    [])
    0.51
     Romano
    0.50
    cmath
    0.48
     })
    0.47
    ariously
    0.47
    шал
    0.47
    oused
    0.47
     NFA
    0.46
    ாக
    0.46
    Activations Density 0.018%

    No Known Activations