© 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. 4-CLT-HP
    7. 2953
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    <bos>
    -0.57
    topping
    -0.45
    }];
    -0.44
    asyarakat
    -0.43
     dizem
    -0.41
    }}}}
    -0.39
    arote
    -0.38
     topping
    -0.38
     sako
    -0.37
     vela
    -0.37
    POSITIVE LOGITS
    SourceChecksum
    0.82
     <<<<<<<<<<<<<<
    0.68
    AndEndTag
    0.65
     Creek
    0.63
    yarnpkg
    0.63
    thâu
    0.60
     Valley
    0.59
    بوابة
    0.59
     tartalomajánló
    0.59
    Datuak
    0.59
    Activations Density 0.004%

    No Known Activations