© 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. 3083
    Prev
    Next
    INDEX
    Explanations

    Sentence beginnings and "as"

    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
    IndentedString
    -0.69
     the
    -0.63
    oa̍t
    -0.62
    DotNetBar
    -0.58
    "]));
    -0.55
    AllowUser
    -0.54
    }`;
    -0.53
     invokingState
    -0.52
    ]]);
    -0.50
     CGSize
    -0.50
    POSITIVE LOGITS
     likely
    0.65
     Likely
    0.65
    StoryboardSegue
    0.63
    Likely
    0.59
    enschappelijke
    0.59
    RectangleBorder
    0.58
     الدولى
    0.57
    Much
    0.57
     TAMBÉM
    0.55
    much
    0.54
    Activations Density 0.000%

    No Known Activations