© 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. 98042
    Prev
    Next
    INDEX
    Explanations

    months

    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
     overnight
    -0.50
    sb
    -0.45
    sche
    -0.45
     sooner
    -0.44
    R
    -0.43
    一言
    -0.42
    WER
    -0.41
    いざ
    -0.41
    一夜
    -0.40
     gé
    -0.40
    POSITIVE LOGITS
     estekak
    0.69
    "]];
    0.68
    __":
    0.66
    enderror
    0.64
    InstanceState
    0.63
    dafx
    0.63
     ويكيميديا
    0.63
    __':
    0.63
    DebuggerNonUser
    0.63
    URLException
    0.62
    Activations Density 0.014%

    No Known Activations